research paper on text classification

Subscribe to the PwC Newsletter

Join the community, add a new evaluation result row, text classification.

1171 papers with code • 92 benchmarks • 145 datasets

Text Classification is the task of assigning a sentence or document an appropriate category. The categories depend on the chosen dataset and can range from topics.

Text Classification problems include emotion classification, news classification, citation intent classification, among others. Benchmark datasets for evaluating text classification capabilities include GLUE, AGNews, among others.

In recent years, deep learning techniques like XLNet and RoBERTa have attained some of the biggest performance jumps for text classification problems.

( Image credit: Text Classification Algorithms: A Survey )

Benchmarks Add a Result

--> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> --> -->

Trend	Dataset	Best Model	Paper	Code	Compare
		ST5-XXL
		XLNet
		XLNet
		DeBERTa
		Automatic Label Error Correction
		LinearSVM+TFIDF
		BERT-ITPT-FiT
		RoBERTaGCN
		BERT-ITPT-FiT
		VLAWE
		1-6 BertGCN
		Human (Post-Rec.) (Spangher et al., 2021)
		HAHNN (CNN)
		ULMFiT (pre-trained vocab, no gradual unfreezing)
		CNN + CRF
		CNN + CRF
		BERT-FP-LBL
		RoBERTa-RF-T1 hybrid
		Character-BERT+RS
		XLNet
		XLNet
		One-hot CNN+ Johnson & Zhang ([2016b])
		Protoformer
		Space-XLNet
		BERT-ITPT-FiT
		XLNet
		Custom Legal-BERT
		Custom Legal-BERT
		BioLinkBERT (large)
		ERNIE 2.0
		Logistic Regression
		Rules
		Naive Bayes using Tf-idf features
		TRANS-BLSTM
		Longformer
		DistilBERT
		DeBERTa
		Vicuna13B v1.1
		Space-BERT
		BERT
		BERT
		BERT-based Ensembles
		BigBird
		BigBird
		BigBird
		Our proposed method Model Averaging(D + E + F)
		Our proposed method Model Averaging(D + E + F)
		LSVC + linguistic features + publishing attributes
		RoBERTaGCN
		Pretrained Hierarchical Transformer
		NutCracker
		TRANS-BLSTM
		TRANS-BLSTM
		TRANS-BLSTM
		TRANS-BLSTM
		RoBERTa-Large + ICDA
		Spark NLP
		BERT
		BERT
		RoBERTa
		DeBERTa
		ERNIE 2.0
		Logistic Regression
		Flair

Most implemented papers

Bert: pre-training of deep bidirectional transformers for language understanding.

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers.

Semi-supervised Sequence Learning

In our experiments, we find that long short term memory recurrent networks after being pretrained with the two approaches are more stable and generalize better.

Universal Language Model Fine-tuning for Text Classification

Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch.

Bag of Tricks for Efficient Text Classification

facebookresearch/fastText • EACL 2017

This paper explores a simple and efficient baseline for text classification.

RoBERTa: A Robustly Optimized BERT Pretraining Approach

Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging.

FastText.zip: Compressing text classification models

facebookresearch/fastText • 12 Dec 2016

We consider the problem of producing compact architectures for text classification, such that the full model fits in a limited amount of memory.

Character-level Convolutional Networks for Text Classification

This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification.

Distributed Representations of Sentences and Documents

Its construction gives our algorithm the potential to overcome the weaknesses of bag-of-words models.

Revisiting Semi-Supervised Learning with Graph Embeddings

We present a semi-supervised learning framework based on graph embeddings.

Universal Sentence Encoder

For both variants, we investigate and report the relationship between model complexity, resource consumption, the availability of transfer task training data, and task performance.

A Survey on Text Classification: From Traditional to Deep Learning

New citation alert added.

This alert has been successfully added and will be sent to:

You will be notified whenever a record that you have chosen has been cited.

To manage your alert preferences, click on the button below.

New Citation Alert!

Please log in to your account

Information & Contributors

Bibliometrics & citations, view options, 1 introduction.

1.1 Major Differences and Contributions

Datasets	#C	#L	#N	Language	Related Papers	Sources	Applications
MR	2	20	10,662	English	[ , , , ]	[ ]	SA
SST-1	5	18	11,855	English	[ , ] [ , ][ ]	[ ]	SA
SST-2	2	19	9,613	English	[ , , ] [ , ]	[ ]	SA
MPQA	2	3	10,606	English	[ , , ]	[ ]	SA
IMDB	2	294	50,000	English	[ ][ ] [ ] [ ] [ ]	[ ]	SA
Yelp.P	2	153	598,000	English	[ , ]	[ ]	SA
Yelp.F	5	155	700,000	English	[ , , ]	[ ]	SA
Amz.P	2	91	4,000,000	English	[ , ]	[ ]	SA
Amz.F	5	93	3,650,000	English	[ , , ]	[ ]	SA
Twitter	3	19	11,209	English	[ ][ ]	[ ]	SA
NLP & CC 2013	2	-	115,606	Multi-language	[ ]	[ ]	SA
20NG	20	221	18,846	English	[ , , , , ]	[ ]	NC
AG News	4	45/7	127,600	English	[ , ] [ , ]	[ ]	NC
R8	8	66	7,674	English	[ , ] [ ]	[ ]	NC
R52	52	70	9,100	English	[ , ] [ ]	[ ]	NC
Sogou	6	578	510,000	Chinese	[ ]	[ ]	NC
Newsgroup	20	-	18,846	English	[ ]	[ ]	NC
DBPedia	14	55	630,000	English	[ , , , ]	[ ]	TL
Ohsumed	23	136	7,400	English	[ , , ]	[ ]	TL
YahooA	10	112	1,460,000	English	[ , ]	[ ]	TL
EUR-Lex	3,956	1,239	19,314	English	[ ] [ , ] [ ]	[ ]	TL
Amazon670K	670	244	643,474	English	[ , ]	[ ]	TL
Google news	152	6	11,109	English	[ , , ]	[ ]	TL
TweetSet 2011-2012	89	-	2,472	English	[ , ]	[ ]	TL
TweetSet 2011-2015	269	8	30,322	English	[ , ]	[ ]	TL
Bing	4	20	34,871	English	[ ]	[ ]	TL
Fudan	20	2981	18,655	Chinese	[ ]	[ ]	TL
SQuAD	-	5,000	5,570	English	[ , , , ]	[ ]	QA
TREC-QA	-	1,162	68	English	[ ]	[ ]	QA
TREC	6	10	5,952	English	[ , , ] [ ]	[ ]	QA
WikiQA	-	873	243	English	[ , ]	[ ]	QA
Subj	2	23	10,000	English	[ , , ]	[ ]	QA
CR	2	19	3,775	English	[ , ]	[ ]	QA
Reuters	90	168	10,788	English	[ , ]	[ ]	ML
Reuters10	10	168	9,979	English	[ ]	[ ]	ML
RCV1	103	240	807,595	English	[ , , , ]	[ ]	ML
RCV1-V2	103	124	804,414	English	[ , ]	[ ]	ML
AAPD	54	163	55,840	English	[ , ]	[ ]	ML

1.2 Organization of the Survey

2 text classification methods, 2.1 traditional models.

2.1.1 PGM-based Methods.

2.1.2 KNN-based Methods.

2.1.3 SVM-based Methods.

2.1.4 dt-based methods..

2.1.5 Integration-based Methods.

2.2 deep learning models, 2.2.1 renn-based methods..

2.2.2 MLP-based Methods.

2.2.3 rnn-based methods..

2.2.4 CNN-based Methods.

2.2.5 attention-based methods..

2.2.6 Pre-trained Methods.

2.2.7 GNN-based Methods.

2.2.8 Others.

3 datasets and evaluation metrics, 3.1 datasets, 3.1.1 sentiment analysis (sa)., 3.1.2 news classification (nc)., 3.1.3 topic labeling (tl)., 3.1.4 question answering (qa)., 3.1.5 natural language inference (nli)., 3.1.6 multi-label (ml) datasets., 3.1.7 others., 3.2 evaluation metrics.

Notations	Descriptions
\(TP\)	true positive
\(FP\)	false positive
\(TN\)	true negative
\(FN\)	false negative
\(TP_{t}\)	true positive of the \(t\) th label on a text
\(FP_{t}\)	false positive of the \(t\) th label on a text
\(TN_{t}\)	true negative of the \(t\) th label on a text
\(FN_{t}\)	false negative of the \(t\) th label on a text
\(\mathcal {S}\)	label set of all samples
\({Q}\)	the number of predicted labels on each text

3.2.1 Single-label Metrics.

3.2.2 multi-label metrics., 4 quantitative results.

5 Future Research Challenges

5.1 challenges from data perspective, 5.2 challenges from model perspective, 5.3 challenges from performance perspective, 6 conclusion, acknowledgments.

Murodov P Prutzkow A (2024) MATHEMATICAL MODEL OF FUZZY DEFINITION OF SUBJECTS OF SCIENTIFIC ARTICLES USING SYNTACTICALLY RELATED WORDS THE BULLETIN OF THE TAJIK NATIONAL UNIVERSITY. SERIES OF ECONOMIC AND SOCIAL SCIENCES 10.62965/tnu.sns.2024.2.2 2024 :2 Online publication date: 29-Mar-2024 https://doi.org/10.62965/tnu.sns.2024.2.2
Mansilla Ancco S Pérez Treviños M (2024) Clasificación de comentarios de Android usando BERT Innovación y Software 10.48168/innosoft.s15.a120 5 :1 (94-110) Online publication date: 30-Mar-2024 https://doi.org/10.48168/innosoft.s15.a120
Jeong D Jeong B Ji S (2024) Leveraging Machine Learning to Analyze Semantic User Interactions in Visual Analytics Information 10.3390/info15060351 15 :6 (351) Online publication date: 13-Jun-2024 https://doi.org/10.3390/info15060351
Show More Cited By

Index Terms

General and reference

Document types

Surveys and overviews

Recommendations

Deep learning--based text classification: a comprehensive review.

Deep learning--based models have surpassed classical machine learning--based approaches in various text classification tasks, including sentiment analysis, news categorization, question answering, and natural language inference. In this article, we ...

Chinese text classification by the Naïve Bayes Classifier and the associative classifier with multiple confidence threshold values

Each type of classifier has its own advantages as well as certain shortcomings. In this paper, we take the advantages of the associative classifier and the Naive Bayes Classifier to make up the shortcomings of each other, thus improving the accuracy of ...

Exploring Video Captioning Techniques: A Comprehensive Survey on Deep Learning Methods

Video captioning is an automated collection of natural language phrases that explains the contents in video frames. Because of the incomparable performance of deep learning in the field of computer vision and natural language processing in recent ...

Information

Published in.

cover image ACM Transactions on Intelligent Systems and Technology

Arizona State University, USA

Association for Computing Machinery

New York, NY, United States

Publication History

Permissions, check for updates, author tags.

Deep learning
traditional models
text classification
evaluation metrics

Funding Sources

National Key R&D Program of China
State Key Laboratory of Software Development Environment
Lehigh’s accelerator
CAAI-Huawei MindSpore Open Fund

Contributors

Other metrics, bibliometrics, article metrics.

124 Total Citations View Citations
17,470 Total Downloads
Downloads (Last 12 months) 11,747
Downloads (Last 6 weeks) 1,371
Sudarshan Joshi Akshay Bachkar Omkar Awaje Rhutuj Bhoir Kimaya Urane (2024) Automated Answersheet Evaluation using BERT International Journal of Scientific Research in Computer Science, Engineering and Information Technology 10.32628/CSEIT2410337 10 :3 (624-631) Online publication date: 24-Jun-2024 https://doi.org/10.32628/CSEIT2410337
LUO J HE C LUO H (2024) BRsyn-Caps: Chinese Text Classification Using Capsule Network Based on Bert and Dependency Syntax IEICE Transactions on Information and Systems 10.1587/transinf.2023EDP7119 E107.D :2 (212-219) Online publication date: 1-Feb-2024 https://doi.org/10.1587/transinf.2023EDP7119
Albashayreh A Bandyopadhyay A Zeinali N Zhang M Fan W Gilbertson White S (2024) Natural Language Processing Accurately Differentiates Cancer Symptom Information in Electronic Health Record Narratives JCO Clinical Cancer Informatics 10.1200/CCI.23.00235 Online publication date: Aug-2024 https://doi.org/10.1200/CCI.23.00235
Mitreva E Georgiev V Nikolova A (2024) Classification of Short Noisy Text Proceedings of the International Conference on Computer Systems and Technologies 2024 10.1145/3674912.3674935 (227-231) Online publication date: 14-Jun-2024 https://dl.acm.org/doi/10.1145/3674912.3674935
Yi J Chen Z (2024) Deconfounded Cross-modal Matching for Content-based Micro-video Background Music Recommendation ACM Transactions on Intelligent Systems and Technology 10.1145/3650042 15 :3 (1-25) Online publication date: 15-Apr-2024 https://dl.acm.org/doi/10.1145/3650042
Chen A Rossi R Park N Trivedi P Wang Y Yu T Kim S Dernoncourt F Ahmed N (2024) Fairness-Aware Graph Neural Networks: A Survey ACM Transactions on Knowledge Discovery from Data 10.1145/3649142 18 :6 (1-23) Online publication date: 12-Apr-2024 https://dl.acm.org/doi/10.1145/3649142
Zeng H He Z Yue Z McAuley J Wang D Hui Yang G Wang H Han S Hauff C Zuccon G Zhang Y (2024) Fair Sequential Recommendation without User Demographics Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval 10.1145/3626772.3657703 (395-404) Online publication date: 10-Jul-2024 https://dl.acm.org/doi/10.1145/3626772.3657703

View options

View or Download as a PDF file.

View online with eReader .

HTML Format

View this article in HTML Format.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Share this publication link.

Copying failed.

Share on social media

Affiliations, export citations.

Please download or close your previous search result export first before starting a new bulk export. Preview is not available. By clicking download, a status dialog will open to start the export process. The process may take a few minutes but once it finishes a file will be downloadable from your browser. You may continue to browse the DL while the export process is in progress. Download
Download citation
Copy citation

We are preparing your search results for download ...

We will inform you here when the file is ready.

Your file of search results citations is now ready.

Your search export query has expired. Please try again.

IEEE Account

Change Username/Password
Update Address

Purchase Details

Payment Options
Order History
View Purchased Documents

Profile Information

Communications Preferences
Profession and Education
Technical Interests
US & Canada: +1 800 678 4333
Worldwide: +1 732 981 0060
Contact & Support
About IEEE Xplore
Accessibility
Terms of Use
Nondiscrimination Policy
Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. © Copyright 2024 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.

Improving text classification through pre-attention mechanism-derived lexicons

Published: 02 September 2024

Cite this article

Zhe Wang ORCID: orcid.org/0000-0002-8333-4748 1 ,
Qingbiao Li 2 ,
Bin Wang 1 ,
Tong Wu 1 &
Chengwei Chang 1

A comprehensive and high-quality lexicon plays a crucial role in traditional text classification approaches. It improves the utilization of linguistic knowledge. Although it is helpful for this task, the lexicon has received little attention in current neural network models. First, obtaining a high-quality lexicon is not easy. Second, an effective automated lexicon extraction method is lacking, and most lexicons are handcrafted, which is very inefficient for big data. Finally, there is no effective way to use a lexicon in a neural network. To address these limitations, we propose a pre-attention mechanism for text classification in this study, which can learn the attention values of various words based on their effects on classification tasks. Words with different attention values can form a domain lexicon. Experiments on three publicly available and authoritative benchmark text classification tasks show that our models obtain competitive results compared with state-of-the-art models. For the same dataset, when we use the pre-attention mechanism to obtain attention values, followed by different neural networks, words with high attention values have a high degree of coincidence, which proves the versatility and portability of the pre-attention mechanism. We can obtain stable lexicons using attention values, which is an inspiring method of information extraction.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save.

Get 10 units per month
Download Article/Chapter or eBook
1 Unit = 1 Article or 1 Chapter
Cancel anytime

Price includes VAT (Russian Federation)

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Dual-axial self-attention network for text classification

Word-character attention model for Chinese text classification

CRAN: A Hybrid CNN-RNN Attention-Based Model for Text Classification

Explore related subjects.

Artificial Intelligence

Data Availability and Access

The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.

Revathy G, Alghamdi SA, Alahmari SM, Yonbawi SR, Kumar A, Haq MA (2022) Sentiment analysis using machine learning: progress in the machine intelligence for data science. Sustain Energy Technol Assessments 53:102557

Article Google Scholar

Rizk YE, Asal WM (2021) Sentiment analysis using machine learning and deep learning models on movies reviews. In: 2021 3rd Novel intelligent and leading emerging sciences conference (NILES), pp 129–132

Yang Z, Yang D, Dyer C et al (2016) Rmdl: hierarchical attention networks for document classification. In: Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 1480–1489

Wankhade M, Rao ACS, Kulkarni C (2022) A survey on sentiment analysis methods, applications, and challenges. Artif Intell Rev 55(7):5731–5780

Minaee S, Kalchbrenner N, Cambria E, Nikzad Khasmakhi N, Asgari-Chenaghlu M, Gao J (2021) Deep learning-based text classification: a comprehensive review. ACM Comput Surv 54:1–40

Bandhakavi A et al (2017) Lexicon based feature extraction for emotion text classification. Pattern Recognit Lett 93:133–142

Bandhakavi A, Wiratunga N, Padmanabhan D, Massie S (2017) Lexicon based feature extraction for emotion text classification. Pattern Recognit Lett 93:133–142

Pradhan A, Senapati MR, Sahu PK (2023) Comparative analysis of lexicon-based emotion recognition of text. In: Machine learning, image processing, network security and data sciences, pp 671–677

Chiril P, Pamungkas EW, Benamara F, Moriceau V, Patti V (2022) Emotionally informed hate speech detection: a multi-target perspective. Cogn Comput 1–31

Naithani K, Raiwani YP (2023) Realization of natural language processing and machine learning approaches for text-based sentiment analysis. Expert Syst 40(5):13114

Wen S, Jian L (2018) Recurrent convolutional neural network with attention for twitter and yelp sentiment classification: Arc model for sentiment classification. Proceedings of the 2018 international conference on algorithms, computing and artificial intelligence

Lei Z, Yang Y, Yang M (2018) Sentiment lexicon enhanced attention-based lstm for sentiment classification. In: Proceedings of the AAAI conference on artificial intelligence, vol 32

Tai SK, Richard S, Christopher D (2015) Improved semantic representations from tree-structured long short-term memory networks. Comput Sci 5:0–36

Jianqiang Z, Gui X, Zhang X (2018) Deep convolution neural networks for twitter sentiment analysis. IEEE Access 6:23253–23260

Johnson R, Tong Z (2015) Effective use of word order for text categorization with convolutional neural networks. In: The 2015 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 103–112. The Association for Computational Linguistics, Colorado, USA

Sundermeyer M, Hermann N, Ralf S (2015) From feedforward to recurrent lstm neural networks for language modeling. IEEE/ACM Trans Audio Speech Lang Process 517–529

Tang D, Qin B, Liu T (2015) Document modeling with gated recurrent neural network for sentiment classification. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp 1422–1432

Lin Z, Feng M, Santos NC et al (2017) A structured self-attentive sentence embedding. In: 5th International conference on learning representations. OpenReview.net, Toulon, France

Galassi A, Lippi M, Torroni P (2019) Attention in natural language processing. IEEE Trans Neural Netw Learn Syst 32:4291–4308

Bao Y et al (2018) Deriving machine attention from human rationales. Proceedings of the 2018 conference on empirical methods in natural language processing, pp 1903–1913

Yue W, Zhu C, Gao Y (2021) Bilstm chinese text sentiment analysis based on pre-attention. World Sci Res J 7(6):33–42

Google Scholar

Xiaoyan L, Raga RC (2023) Bilstm model with attention mechanism for sentiment classification on chinese mixed text comments. IEEE Access 11:26199–26210

Zarrieß S, Voigt H, Schüz S (2021) Decoding methods in neural language generation: a survey. Information 12(9):355

Zhang N, Kim J (2023) A survey on attention mechanism in nlp. In: 2023 International conference on electronics, information, and communication (ICEIC), pp 1–4

Fu T, Gao S, Zhao X, Wen J-R, Yan R (2022) Learning towards conversational ai: a survey. AI Open 3:14–28

Hassan SU, Ahamed J, Ahmad K (2022) Analytics of machine learning-based algorithms for text classification. Sust Oper Comput 3:238–248

Li Q, Peng H, Li J, Xia C, Yang R, Sun L, Yu PS, He L (2022) A survey on text classification: from traditional to deep learning. ACM Trans Intell Syst Technol (TIST) 13(2):1–41

Hameed Z, Garcia-Zapirain B (2020) Sentiment classification using a single-layered bilstm model. IEEE Access 8:73992–74001

Mikolov T, Sutskever I, Chen K et al (2018) Distributed representations of words and phrases and their compositionality. In: Proceedings of the 2nd international conference on information system and data mining. ACM, pp 19–28

Zhang R, Lee H, Radev D (2018) Dependency sensitive convolutional neural networks for modeling sentences and documents. In: Proceedings of the 2016 conference of the north american chapter of the association for computational linguistics: human language technologies, pp 1512–1521. Association for Computational Linguistics, San Diego, California

Wieting J, Kiela D (2019) No training required: exploring random encoders for sentence classification. International conference on learning representations (2019)

Zhang D, Tian L, Hong M et al (2018) Combining convolution neural network and bidirectional gated recurrent unit for sentence semantic classification. IEEE Access 6:73750–73759

Zhang Y, Wallace B (2017) A sensitivity analysis of (and practitioners’ guide to) convolutional neural networks for sentence classification. Proceedings of the The 8th international joint conference on natural language processing, pp 253–263

Kowsari K, Heidarysafa M, Brown ED et al (2013) Rmdl: random multimodel deep learning for classification. Advances in neural information processing systems, pp 3111–3119

Cen P, Zhang K, Zheng D (2020) Sentiment analysis using deep learning approach. J Artif Intell 2(1):17–27

Chen K, Zhang Z, Long J et al (2016) Turning from tf-idf to tf-igm for term weighting in text classification. Expert Syst Appl 66:245–260

Patel A, Tiwari AK, Ahmad S (2022) An efficient approach for sentiment analysis using convolutional neural network. In: Proceedings of the 3rd international conference on advanced computing and software engineering

Dahir UM, Alkindy FK (2023) Utilizing machine learning for sentiment analysis of imdb movie review data. Int J Eng Trends Technol 71:18–26

Danyal MM, Khan SS, Khan M, Ghaffar MB, Khan B, Arshad M (2023) Sentiment analysis based on performance of linear support vector machine and multinomial naïve bayes using movie reviews with baseline techniques. J Big Data 5

Song Z, Yin Z, Yuan Z, Zhang C, Chi W, Ling Y, Zhang S (2021) Attention-oriented action recognition for real- time human-robot interaction. In: 2020 25th International conference on pattern recognition (ICPR), pp 7087–7094. IEEE Computer Society, Los Alamitos, CA, USA

He Z, Lin R, Wu B, Zhao X, Zou H (2023) Pre-attention mechanism and convolutional neural network based multivariate load prediction for demand response. Energies 16(8):3446

Download references

Author information

Authors and affiliations.

Beijing Institute of Computer Technology and Applications, Second Academy of China Aerospace Science and Industry Corporation, No.51 Yongding Road, Haidian District, Beijing, 100854, China

Zhe Wang, Bin Wang, Tong Wu & Chengwei Chang

School of Computer Science, Beijing University of Posts and Telecommunications, No.10 Xitucheng Road, Haidian District, Beijing, 100876, China

Qingbiao Li

You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization, Z.W. and Q.-B.L. ; Data curation, Q.-B.L. and B.W. ; Methodology, T.W. and Z.W. ; Validation, Z.W. and Q.-B.L.; Writing-original draft, Z.W.; Writing-review & editing, Z.W. and Q.-B.L.; Project administration, B.W. and T.W. ; Funding acquisition, C.-W.C. and B.W.

Corresponding author

Correspondence to Zhe Wang .

Ethics declarations

Competing interests.

The authors declare no conflicts of interest. The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Ethics Approval

This paper has been published with the written informed consent of all authors.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Wang, Z., Li, Q., Wang, B. et al. Improving text classification through pre-attention mechanism-derived lexicons. Appl Intell (2024). https://doi.org/10.1007/s10489-024-05742-1

Download citation

Accepted : 04 August 2024

Published : 02 September 2024

DOI : https://doi.org/10.1007/s10489-024-05742-1

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Text classification
Lexicon extraction
Pre-attention mechanism
Find a journal
Publish with us
Track your research

Sep 01, 2022

Article Menu

Subscribe SciFeed
Recommended Articles
Google Scholar
on Google Scholar
Table of Contents

Find support for a specific problem in the support section of our website.

Please let us know what you think of our products and services.

Visit our dedicated information section to learn more about MDPI.

JSmol Viewer

Research on a real-time, high-precision end-to-end sorting system for fresh-cut flowers, 1. introduction, 2. materials and methods, 2.1. experimental design, 2.2. rgbd flower sorting dataset, 2.2.1. depth image acquisition, 2.2.2. image preprocessing, 2.3. mtmd-yolo detection model, 2.3.1. feature fusion, 2.3.2. double-label detection head, 2.3.3. double-label nms, 2.3.4. loss function of multi-task, 2.4. experiment setting and evaluation indicators, 3. experimental results and analysis, 3.1. optimization experiment, 3.1.1. feature fusion optimization, 3.1.2. weight optimization of the loss function, 3.2. experiments contrast, 3.2.1. ablation experiments, 3.2.2. contrast experiments, 3.3. detection results in challenging conditions, 3.3.1. experiments on difficult-to-distinguish maturity of flower, 3.3.2. detection effects in real-world environments, 3.4. innovations, limitations, and future work, 4. conclusions, author contributions, institutional review board statement, informed consent statement, data availability statement, acknowledgments, conflicts of interest.

Aman, M. Postharvest loss estimation of cut rose ( Rosa hybrida ) flower farms: Economic analysis in East Shoa Zone, Ethiopia. Int. J. Sustain. Econ. 2014 , 6 , 82–95. [ Google Scholar ] [ CrossRef ]
Tiay, T.; Benyaphaichit, P.; Riyamongkol, P. Flower recognition system based on image processing. In Proceedings of the 2014 Third ICT International Student Project Conference (ICT-ISPC), Nakhonpathom, Thailand, 26–27 March 2014; pp. 99–102. [ Google Scholar ]
Zawbaa, H.M.; Abbass, M.; Basha, S.H.; Hazman, M.; Hassenian, A.E. An automatic flower classification approach using machine learning algorithms. In Proceedings of the 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Delhi, India, 24–27 September 2014; pp. 895–901. [ Google Scholar ]
Albadarneh, A.A. Automated Flower Species Detection and Recognition from Digital Images ; Princess Sumaya University for Technology: Amman, Jordan, 2016. [ Google Scholar ]
Liu, W.; Rao, Y.; Fan, B.; Song, J.; Wang, Q. Flower classification using fusion descriptor and SVM. In Proceedings of the 2017 International Smart Cities Conference (ISC2), Wuxi, China, 14–17 September 2017; pp. 1–4. [ Google Scholar ]
Soleimanipour, A.; Chegini, G.R.; Massah, J. Classification of Anthurium flowers using combination of PCA, LDA and support vector machine. Agric. Eng. Int. CIGR J. 2018 , 20 , 219–228. [ Google Scholar ]
Patel, I.; Patel, S. Flower identification and classification using computer vision and machine learning techniques. Int. J. Eng. Adv. Technol. (IJEAT) 2019 , 8 , 277–285. [ Google Scholar ] [ CrossRef ]
Tian, M.; Chen, H.; Wang, Q. Flower identification based on Deep Learning. J. Phys. Conf. Ser. 2019 , 1237 , 022060. [ Google Scholar ] [ CrossRef ]
Anjani, I.A.; Pratiwi, Y.R.; Nurhuda, S.N.B. Implementation of deep learning using convolutional neural network algorithm for classification rose flower. J. Phys. Conf. Ser. 2021 , 1842 , 012002. [ Google Scholar ] [ CrossRef ]
Cıbuk, M.; Budak, U.; Guo, Y.; Ince, M.C.; Sengur, A. Efficient deep features selections and classification for flower species recognition. Measurement 2019 , 137 , 7–13. [ Google Scholar ] [ CrossRef ]
Ren, S.; He, K.; Girshick, R.; Sun, J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans. Pattern Anal. Mach. Intell. 2016 , 39 , 1137–1149. [ Google Scholar ] [ CrossRef ]
Cai, Z.; Vasconcelos, N. Cascade r-cnn: Delving into high quality object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 6154–6162. [ Google Scholar ]
He, K.; Gkioxari, G.; Dollár, P.; Girshick, R. Mask r-cnn. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 2961–2969. [ Google Scholar ]
Redmon, J.; Farhadi, A. Yolov3: An incremental improvement. arXiv 2018 , arXiv:1804.02767. [ Google Scholar ]
Li, C.; Li, L.; Jiang, H.; Weng, K.; Geng, Y.; Li, L.; Ke, Z.; Li, Q.; Cheng, M.; Nie, W. YOLOv6: A single-stage object detection framework for industrial applications. arXiv 2022 , arXiv:2209.02976. [ Google Scholar ]
Reis, D.; Kupec, J.; Hong, J.; Daoudi, A. Real-time flying object detection with YOLOv8. arXiv 2023 , arXiv:2305.09972. [ Google Scholar ]
Liu, W.; Anguelov, D.; Erhan, D.; Szegedy, C.; Reed, S.; Fu, C.-Y.; Berg, A.C. Ssd: Single shot multibox detector. In Proceedings of the Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, 11–14 October 2016; Proceedings, Part I 14. pp. 21–37. [ Google Scholar ]
Fu, C.-Y.; Liu, W.; Ranga, A.; Tyagi, A.; Berg, A.C. Dssd: Deconvolutional single shot detector. arXiv 2017 , arXiv:1701.06659. [ Google Scholar ]
Krishna, K.P.; Thomas, G.; Soumya, M.; Praneetha, K.; Imrana, A. You Only Look Once for Panoptic Driving Perception (YOLOP). EPRA Int. J. Multidiscip. Res. (IJMR) 2022 , 8 , 55–61. [ Google Scholar ]
Gao, Y.; Li, Z.; Li, B.; Zhang, L. YOLOv8MS: Algorithm for Solving Difficulties in Multiple Object Tracking of Simulated Corn Combining Feature Fusion Network and Attention Mechanism. Agriculture 2024 , 14 , 907. [ Google Scholar ] [ CrossRef ]
Sun, X.; Li, Z.; Zhu, T.; Ni, C. Four-dimension deep learning method for flower quality grading with depth information. Electronics 2021 , 10 , 2353. [ Google Scholar ] [ CrossRef ]
Fei, Y.; Li, Z.; Zhu, T.; Ni, C. A lightweight attention-based Convolutional Neural Networks for fresh-cut flower classification. IEEE Access 2023 , 11 , 17283–17293. [ Google Scholar ] [ CrossRef ]
Neubeck, A.; Van Gool, L. Efficient non-maximum suppression. In Proceedings of the 18th International Conference on Pattern Recognition (ICPR’06), Hong Kong, China, 20–24 August 2006; pp. 850–855. [ Google Scholar ]
Patro, S.; Sahu, K.K. Normalization: A preprocessing stage. arXiv 2015 , arXiv:1503.06462. [ Google Scholar ] [ CrossRef ]
Quality Grade of Fresh Cut Flower Auction Products Part 2: Single Rose. 2014. Available online: https://hbba.sacinfo.org.cn/stdDetail/975d7254c55992f9797c99a36e366404 (accessed on 16 July 2024).
Lin, T.-Y.; Dollár, P.; Girshick, R.; He, K.; Hariharan, B.; Belongie, S. Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21–26 July 2017; pp. 2117–2125. [ Google Scholar ]
Liu, S.; Qi, L.; Qin, H.; Shi, J.; Jia, J. Path aggregation network for instance segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 8759–8768. [ Google Scholar ]
Zheng, Z.; Wang, P.; Ren, D.; Liu, W.; Ye, R.; Hu, Q.; Zuo, W. Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybern. 2021 , 52 , 8574–8586. [ Google Scholar ] [ CrossRef ] [ PubMed ]
Mao, A.; Mohri, M.; Zhong, Y. Cross-entropy loss functions: Theoretical analysis and applications. In Proceedings of the International Conference on Machine Learning, Hangzhou, China, 23–29 July 2023; pp. 23803–23828. [ Google Scholar ]

Click here to enlarge figure

Method	mAP (%) ↑	Params (M) ↓
P3~P4	90.14	1.90
P4~P5	97.81	6.46
P3~P5	94.32	7.03

Baseline	Feature Fusion	RGBD	Multi-Task	Loss Function Optimization	AP (%) ↑	AR (%) ↑	mAP (%) ↑	Speed (FPS) ↑
√					99.98	100	97.17	76.49
√	√				99.98	100	97.75 (+0.62)	90.69
√	√	√			99.98	100	98.13 (+0.38)	81.22
√	√	√	√		99.98	100	98.19 (+0.06)	73.01
√	√	√	√	√	100 (+0.02)	100	98.19	73.07

Baseline	Feature Fusion	RGBD	Multi-Task	Loss Function Optimization	AP (%) ↑	AR (%) ↑	mAP (%) ↑	Speed (FPS) ↑
√					75.68	86.18	85.45	76.45
√	√				83.95 (+8.27)	91.38 (+5.20)	91.61 (+6.16)	90.79
√	√	√			91.21 (+7.26)	93.39 (+2.01)	95.24 (+3.63)	81.25
√	√	√	√		98.24 (+7.03)	98.48 (+5.09)	97.11 (+1.87)	73.01
√	√	√	√	√	99.57 (+1.33)	99.17 (+0.69)	97.81 (+0.70)	73.07

Indicators	P (%)	R (%)	mAP (%)	F1 (%)	P (%)	R (%)	mAP (%)	F1 (%)
RGB	99.98	100	97.75	100	83.95	91.38	91.61	87.03
RGBD	99.98	100	98.13	100	91.21	93.39	95.24	92.15

Indicators	F1 (%)	mAP (%)	Params (M)	Speed (FPS)	F1 (%)	mAP (%)	Params (M)	Speed (FPS)
Single task	100	98.13	6.45	81.22	92.15	95.24	6.45	81.25
Multi-task	100	98.19	6.46	73.01	99.01	97.11	6.46	73.01

Method	Size (Pixels)	AP (%) ↑	AR (%) ↑	mAP (%) ↑	Params (M) ↓	Speed (FPS) ↑
SSD	300 × 300	96.05	93.52	98.95	6.96	42.86
RetinaNet	600 × 600	99.71	96.34	99.70	4.02	89.85
YOLOv5	640 × 640	99.98	100	97.17	7.02	76.49
YOLOv6	640 × 640	96.87	98.14	96.82	18.50	56.47
YOLOv7	640 × 640	100	100	97.22	36.50	23.55
YOLOv8	640 × 640	99.99	100	98.86	11.13	60.85
MTMD-YOLO (This work)	640 × 640	100	100	98.19	6.46	73.07

Method	Size (Pixels)	AP (%) ↑	AR (%) ↑	mAP (%) ↑	Params (M) ↓	Speed (FPS) ↑
SSD	300 × 300	78.75	89.82	78.72	6.96	42.86
RetinaNet	600 × 600	83.76	83.41	83.74	4.02	89.85
YOLOv5	640 × 640	75.68	86.18	85.45	7.02	76.45
YOLOv6	640 × 640	82.47	97.73	82.35	18.50	55.84
YOLOv7	640 × 640	75.78	84.32	83.51	36.50	24.24
YOLOv8	640 × 640	93.79	95.05	97.13	11.13	60.40
MTMD-YOLO (This work)	640 × 640	99.57	99.17	97.81	6.46	73.07

Method	mAP (%)	mAP (%)	Speed (FPS)
RetinaNet	97.70	83.74	45
YOLOv5	97.18	86.12	32
YOLOv8	98.86	97.13	29
MTMD-YOLO (This work)	98.15	97.80	37

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

Duan, Z.; Liu, W.; Zeng, S.; Zhu, C.; Chen, L.; Cui, W. Research on a Real-Time, High-Precision End-to-End Sorting System for Fresh-Cut Flowers. Agriculture 2024 , 14 , 1532. https://doi.org/10.3390/agriculture14091532

Duan Z, Liu W, Zeng S, Zhu C, Chen L, Cui W. Research on a Real-Time, High-Precision End-to-End Sorting System for Fresh-Cut Flowers. Agriculture . 2024; 14(9):1532. https://doi.org/10.3390/agriculture14091532

Duan, Zhaoyan, Weihua Liu, Shan Zeng, Chenwei Zhu, Liangyan Chen, and Wentao Cui. 2024. "Research on a Real-Time, High-Precision End-to-End Sorting System for Fresh-Cut Flowers" Agriculture 14, no. 9: 1532. https://doi.org/10.3390/agriculture14091532

Article Metrics

Article access statistics, further information, mdpi initiatives, follow mdpi.

Subscribe to receive issue release notifications and newsletters from MDPI journals

Open access
Published: 02 September 2024

Knowledge of antimicrobial stewardship and the Access, Watch and Reserve (AWaRe) classification of antibiotics among frontline healthcare professionals in Akwa Ibom State, Nigeria: a cross-sectional study

Mary R. Akpan ORCID: orcid.org/0000-0001-8036-8136 1 ,
Idongesit L. Jackson ORCID: orcid.org/0000-0003-3460-7233 1 ,
Unyime I. Eshiet ORCID: orcid.org/0000-0003-4388-1517 1 ,
Sediong A. Mfon ORCID: orcid.org/0009-0000-6778-8419 1 &
Ekpema A. Abasiattai ORCID: orcid.org/0009-0007-0480-0266 2

BMC Health Services Research volume 24 , Article number: 1014 ( 2024 ) Cite this article

Metrics details

Antimicrobial stewardship (AMS) aims to improve antibiotic use while reducing resistance and its consequences. There is a paucity of data on the availability of AMS programmes in southern Nigeria. Further, there is no data on Nigerian healthcare professionals’ knowledge of the WHO ‘Access, Watch and Reserve’ (AWaRe) classification of antibiotics. This study sought to assess knowledge of AMS and the AWaRe classification of antibiotics among frontline healthcare professionals in Akwa Ibom State, Nigeria.

This was a cross-sectional survey of 417 healthcare professionals, comprising medical doctors, pharmacists and nurses, across 17 public hospitals in Akwa Ibom State, Nigeria. A paper-based self-completion questionnaire was used to collect data from the participants during working hours between September and November 2023. Statistical analysis was done using SPSS version 25.0, with p < 0.05 indicating statistical significance.

Four hundred and seventeen out of the 500 healthcare professionals approached agreed to participate, giving an 83.4% response rate. Most of the participants were female (62.1%) and nurses (46.3%). Approximately 57% of participants were familiar with the term antibiotic/antimicrobial stewardship, however, only 46.5% selected the correct description of AMS. Majority (53.0%) did not know if AMS programme was available in their hospitals. 79% of participants did not know about AWaRe classification of antibiotics. Among the 87 (20.9%) who knew, 28.7% correctly identified antibiotics into the AWaRe groups from a given list. Only profession significantly predicted knowledge of AMS and awareness of the AWaRe classification of antibiotics ( p < 0.001). Pharmacists were more likely to define AMS correctly than medical doctors (odds ratio [OR] = 2.02, 95% confidence interval [CI] = 1.16–3.52, p = 0.012), whereas nurses were less likely to be aware of the WHO AWaRe classification of antibiotics than medical doctors (OR = 0.36, 95% CI = 0.18–0.72, p = 0.004).

Conclusions

There was a notable knowledge deficit in both AMS and the AWaRe classification of antibiotics among participants in this study. This highlights the need for educational interventions targeted at the different cadres of healthcare professionals on the role of AMS programmes in reducing antimicrobial resistance and its consequences.

Peer Review reports

Introduction

Antimicrobial resistance (AMR) is ranked fifth among the World Health Organisation’s (WHO) top ten global public health threats [ 1 ]. Available reports showed that an estimated 4·95 million deaths in 2019 were associated with AMR, with western sub-Saharan Africa recording highest death rate at 27·3 deaths per 100 000 [ 2 ]. Antimicrobial stewardship (AMS) has been promoted at international and national levels as a set of coordinated interventions required to improve antibiotic use and reduce resistance and associated morbidity and mortality [ 3 , 4 , 5 , 6 , 7 ]. To support AMS effort at local, national and global levels, the Antibiotics Working Group for the 21st WHO Model List of Essential Medicines adopted the ‘Access, Watch and Reserve’ (AWaRe) classification of antibiotics in the Essential Medicines List [ 8 ]. This classification, which was adopted and endorsed by G20 Health Ministers in October 2018, has since been updated and currently contains 258 antibiotics. The WHO 13th General Programme of Work 2019–2023 recommended that at least 60% of total country-level antibiotic consumption should come from Access group antibiotics [ 9 ].

There is a paucity of data on the availability and/or implementation of AMS programmes in African countries. Although a previous systematic review on the implementation of AMS programmes in African countries found no data on established hospital AMS programme in Nigeria, [ 10 ] a recent study of 20 hospitals randomly selected from the six geopolitical zones of the country to assess AMS implementation and practice reported that only six (30%) of the 20 hospitals had AMS committees with no regular AMS-related activities [ 11 ]. Successful implementation of hospital AMS programmes relies on active participation of healthcare professionals, including medical doctors with expertise in infectious diseases, pharmacists, among others [ 12 , 13 ]. To this end, the WHO global action plan on AMR emphasised improved awareness and understanding of the link between antibiotic use and development of resistance among healthcare professionals in order to optimise antibiotic use [ 14 ]. The objectives of this study therefore were to assess knowledge of AMS and the AWaRe classification of antibiotics among frontline healthcare professionals. Additionally, the study sought to assess the availability and/or implementation of AMS programmes in public hospitals in Akwa Ibom State, Nigeria.

Study design, population and setting

This was a cross-sectional survey. Participants were included purposively based on profession, if they were medical doctors, pharmacists or nurses and work in public secondary or tertiary healthcare hospitals in Akwa Ibom State. Participants were drawn from 16 state-run secondary care hospitals and one tertiary care hospital. The Raosoft online sample size calculator formula for unknown population was used to compute sample size of frontline healthcare professionals to recruit for the study. Using a 95% confidence level, 5% margin of error and population size of 20 000 and assuming 50% response distribution, the recommended sample size was 377. To account for non-response and non-completion of questionnaire, the sample size was increased by 10%; therefore a sample size of 415 frontline healthcare professionals was targeted for this study.

Survey instrument and data collection

A 13-item self-administered paper-based questionnaire was used for data collection in this study (Supplementary file). A set of 15 questionnaire items was initially developed from relevant international documents [ 7 , 8 , 9 ]. To assess content validity, the 15-item questionnaire was sent to two clinical pharmacists who are knowledgeable in questionnaire design and AMS. These experts, who were unconnected to the study, were asked to assess the instrument’s relevance and representativeness of the study objectives. Based on their feedback, two items were dropped: one was unrelated to the study objectives, while the other was redundant. In order to assess face validity, the 13-item survey instrument was administered to 10 professionals (three medical doctors, three pharmacists, and four nurses). Non-response to questionnaire items, time required to complete the questionnaire, and feedback received were used to improve the instrument. The final questionnaire comprised three sections: section A collected demographic information of respondents; section B collected data on knowledge of the term antibiotic/antimicrobial stewardship and the definition/description of AMS. For the description of AMS, six answer options, of which one was correct, were included for participants to select from. Section B also collected data on the availability of AMS in the participating hospitals, while section C contained questions on knowledge of the AWaRe classification of antibiotics. Participants were also asked to identify antibiotics belonging to ‘Access’, ‘Watch’, and ‘Reserve’ groups from a given list of antibiotics. The Cronbach’s alpha coefficient for the survey instrument in this study was 0.67. Data were obtained from the participants during working hours between September and November 2023.

Statistical analysis

Analysis was done using SPSS version 25 (IBM Corp., Amonk, NY). Descriptive statistics was used to present the data. For the item on knowledge of AMS definition, response options were stratified into ‘correct’ and ‘incorrect’. All other options apart from the correct option were coded incorrect. Binary logistic regression was performed to identify the predictors of knowledge of AMS definition and awareness of the WHO AWaRe classification of antibiotics Statistical significance was set at p < 0.05.

Ethical considerations

Ethical approval was obtained from the Health Research Ethics Committees of the Akwa Ibom state Ministry of Health (AKHREC/01/08/23/169; 07/09/2023) and the University of Uyo Teaching hospital (UUTH/AD/S/96/VOLXXI/776; 21/08/2023). Consent to participate in the survey was sought in the questionnaire; participants were required to check a box to consent they agreed to take part in the study.

Four hundred and seventeen out of the 500 healthcare professionals approached agreed to participate, giving an 83.4% response rate.

Participants’ characteristics

A total of 417 frontline healthcare professionals from 17 public hospitals participated in the study, of which majority were female (62.1%, n = 259). 46% ( n = 193) of the participants were nurses, while medical doctors and pharmacists made up 25.4% ( n = 106) and 28.3% ( n = 118), respectively. A summary of the demographic characteristics of participants is provided in Table 1 .

Knowledge of antimicrobial stewardship, antimicrobial stewardship availability and AWaRe classification among healthcare professionals in participating hospitals

Over half (56.8%, n = 237) of the healthcare professionals indicated they had heard the term antibiotic/antimicrobial stewardship. Within the professional cohorts, more than half, 57% ( n = 108) of the nurses indicated they have never heard the term. More than half (53.0%, n = 221) of the healthcare professionals indicated they did not know if AMS programme was available in their hospitals. Among those who indicated that the programme was available in their hospitals, more than half (57.4%) did not select which core element(s) applied to their hospitals.

Regarding the definition/description of AMS, less than half (46.5%, n = 194) of the participants selected the correct description of AMS.

Of the 417 participants, majority (79.1%, n = 330) indicated they have not heard the term ‘Access, Watch, Reserve’ classification of antibiotics. Within each professional group, less than half knew about the AWaRe classification of antibiotics. A summary of the knowledge of AMS, AMS availability and the AWaRe classification is shown in Table 2 .

Knowledge of the AWaRe classification of antibiotics among healthcare professionals

Only 87 (20.9%) health professionals indicated they knew about the AWaRe classification, and attempted questions on the AWaRe classification. Among the 87 who responded ‘yes”, only 25 (28.7%) correctly identified all nine antibiotics from a given list into “Access’, ‘Watch’ and ‘Reserve’. A summary of knowledge of AWaRe classification details and identification of antibiotics belonging to Access, Watch and Reserve is as shown in Table 3 .

Effects of participants’ characteristics on knowledge of antimicrobial stewardship

Table 4 presents the results of binary logistic regression to determine the effects of gender, age, profession and length of practice on the likelihood that participants correctly define AMS. Of the variables assessed, only profession significantly ( p < 0.001) predicted the model. Pharmacists were more likely to define AMS correctly than medical doctors (odds ratio [OR] = 2.02, 95% confidence interval [CI] = 1.16–3.52, p = 0.012).

Effects of participants’ characteristics on knowledge of the AWaRe classification of antibiotics

Results of binary logistic regression to assess the impact of gender, age, profession and length of practice on the likelihood that participants were aware of the WHO AWaRe classification of antibiotics revealed that only profession significantly ( p < 0.001) predicted the model. Nurses were less likely to be aware of the WHO AWaRe classification of antibiotics than medical doctors (OR = 0.36, 95% CI = 0.18–0.72, p = 0.004) (Table 5 ).

A number of studies have investigated the knowledge, attitude and perceptions of healthcare professionals (medical doctors, pharmacists and nurses) towards AMR and the effectiveness of AMS programmes in reducing AMR. Majority of the studies reported that healthcare professionals generally agree on the global and national burden of AMR, the association between antibiotic use in humans and agriculture and the development of resistance, and that AMS can reduce resistance [ 15 , 16 , 17 , 18 ]. Our findings show that more than half of the participants were familiar with the term ‘antibiotic/antimicrobial stewardship’, however, a few of the healthcare professionals selected the correct definition/description of AMS. More than half of the participants did not know if AMS programmes were available in their hospitals, especially among nurses, as well as which core components of AMS applied to their practice setting. A study of knowledge and practices of healthcare professionals towards AMS found that the majority of participants had poor knowledge of AMS, with pharmacists having better knowledge of AMS compared to nurses [ 19 ]. Although nurses have vital roles in hospital AMS, [ 20 , 21 , 22 ] and various models of nurses’ engagement in AMS have been described, [ 23 ] majority of the nurses in our study were not aware of AMS nor the correct description of the term. This finding is consistent with a previous study which found that more than half of the nurses who participated in a study to assess knowledge and attitudes were not familiar with AMS, although about 95% of the nurses believed they had a role in AMS interventions [ 24 ]. There is a likelihood that nurses’ knowledge of AMS may be setting- and/or location-specific. A previous study of nurses’ attitudes toward AMS found that approximately half of the nurses reported familiarity and knowledge of the term AMS [ 25 ]. Furthermore, a study of comparative self-assessment of knowledge on antimicrobials, AMR and AMS between medical doctors, pharmacists and nurses reported that a greater percentage of nurses had higher confidence level on knowledge of all three topics compared to pharmacists and doctors who had less confidence level [ 26 ].

Of the variables assessed, only profession significantly predicted knowledge regarding the definition of AMS. Pharmacists were twice as likely to define AMS correctly as medical doctors. In contrast to our finding, profession was not a significant predictor of AMS knowledge in the study of Sefah et al [ 19 ]. This difference in knowledge between these professions observed in our study may be because, as medicine experts, pharmacists are more aware and conscious of the association between antibiotic use and the development of resistance. The differences in knowledge could also be due to differences in undergraduate curriculum and training, as well as professional focus between pharmacists and medical doctors [ 27 , 28 ]. Prior research involving final-year medical and pharmacy students revealed that a greater proportion of pharmacy students than medical students had received formal instruction in antimicrobial stewardship [ 29 ].

The knowledge gap reported in this study and others [ 12 , 19 , 24 , 26 ] highlights the need for educational interventions such as, meetings, academic detailing, distribution of educational materials and educational outreaches [ 30 ] targeted at different cadres of healthcare professionals. Education is one of the enabling interventions of AMS which has been reported to improve compliance with antibiotic policies alone and in combination with restrictive interventions [ 30 ].

The goal of the AWaRe classification of antibiotics is to reduce AMR. The ‘Watch’ and ’Reserve’ groups of antibiotics are to be prioritised as key targets of stewardship programmes and monitoring to preserve their effectiveness [ 8 , 9 ]. In this study, an overwhelming majority of participants had no idea of the AWaRe classification. Amongst the medical doctors who participated in the study, only about a quarter knew about the AWaRe classification. This finding is of concern because of the risk of overprescribing antibiotics from the ‘Watch’ and “Reserve’ groups, which ought to be used for specific infectious syndromes and in highly specific patients and settings, [ 8 ] respectively. The current recommendation is that at least 60% of antibiotic use should come from the ‘Access’ group antibiotics [ 9 ]. Pharmacists play important roles in AMS, including prospective monitoring of antibiotic use and providing feedback and education on rational prescribing [ 31 ].

Our study revealed that only profession significantly predicted awareness of the WHO AWaRe classification of antibiotics. Although there was no significant difference in the level of awareness of the WHO AWaRe classification between pharmacists and medical doctors, nurses were less likely to be aware of this classification than medical doctors. Older guidelines for hospital AMS, [ 31 , 32 ] however, emphasised the roles of medical doctors and pharmacists in successful implementation rather than nurses’ roles. Nevertheless, the majority of the participants had no knowledge of the AWaRe classification and may therefore be unable to provide education and feedback that can promote the prescribing of the ‘Access’ group antibiotics. Among the few frontline healthcare professionals who knew about the AWaRe classification, less than one-third correctly identified nine antibiotics included in the survey instrument into ‘Access’, ‘Watch’ and ‘Reserve’ groups. The authors are unaware of studies that assessed knowledge of the AWaRe classification of antibiotics among healthcare professionals with which to compare this study findings. Nevertheless, the knowledge gap identified echoes the need for improved awareness of AMR and judicious use of antibiotics in the Watch’ and ‘Reserve’ groups through effective communication, education and training of frontline healthcare professionals.

Limitations

While this study recruited a little above the target sample size, a major limitation is that it was a single-state study, thus findings may not be generalised to other states and practice settings. Furthermore, due to the cross-sectional design of the study, causality cannot be ascertained. As is common with survey research, participant bias, which arises when participants’ responses are deliberately or unintentionally different from their intended responses, is another limitation; selection bias due to the use of the non-probability sampling method in the recruitment of study participants and the possibility of social desirability bias among the participants may have affected the findings of the study.

Overall, there was a notable knowledge deficit in both AMS and the AWaRe classification of antibiotics among healthcare professionals who participated in this study. Educational programmes should be developed for different professional groups to enhance competency and proficiency in AMS to ensure judicious use of antibiotics with a high potential for selection of resistance.

Data availability

The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.

Abbreviations

Antimicrobial resistance

Antimicrobial stewardship

Access, Watch, and Reserve

Confidence interval

Group of 20

Statistical Product and Service Solutions

World Health Organisation

Ten threats to global health in 2019. World Health Organisation. 2019. https://www.who.int/news-room/spotlight/ten-threats-to-global-health-in-2019 . Accessed January 10, 2024.

Murray C, Ikuta K, Sharara F, Swetschinski L, Aguilar G, Gray A, et al. Global burden of bacterial antimicrobial resistance in 2019: a systematic analysis. Lancet. 2022;12(10325):629–55.

Article Google Scholar

Dyar OJ, Huttner B, Schouten J, Pulcini C. What is antimicrobial stewardship? Clin Microbiol Infect. 2017;23(11):793–8.

Article CAS PubMed Google Scholar

Policy guidance on integrated antimicrobial stewardship activities. World Health Organisation. 2021. https://iris.who.int/bitstream/handle/10665/341432/9789240025530-eng.pdf?sequence=1 . Accessed January 10, 2024.

Start smart then focus: antimicrobial stewardship toolkit for inpatient care settings. UK Health Security Agency. 2023. https://www.gov.uk/government/publications/antimicrobial-stewardship-start-smart-then-focus/start-smart-then-focus-antimicrobial-stewardship-toolkit-for-inpatient-care-settings . Accessed January 10, 2024.

Barlam TF, Cosgrove SE, Abbo LM, MacDougall C, Schuetz AN, Septimus EJ, et al. Implementing an antibiotic stewardship program: guidelines by the Infectious Diseases Society of America and the Society for Healthcare Epidemiology of America. Clin Infect Dis. 2016;62:e51.

Article PubMed PubMed Central Google Scholar

Core elements of hospital antibiotic stewardship programs. Centers for Disease Control and Prevention. 2019. https://www.cdc.gov/antibioticuse/healthcare/pdfs/hospitalcore-elements-H.pdf . Accessed January 10, 2024.

Model List of Essential Medicines, 23rd List. World Health Organisation. 2023. https://iris.who.int/bitstream/handle/10665/371090/WHO-MHP-HPS-EML-2023.02-eng.pdf?sequence=1 . Accessed January 10, 2024.

2021 AWaRe classification. World Health Organisation. 2021. https://www.who.int/publications/i/item/2021-aware-classification . Accessed January 10, 2024.

Akpan M, Isemin N, Udoh A, Ashiru-Oredope D. Implementation of antimicrobial stewardship programmes in African countries: a systematic literature review. J Glob Antimicrob Resist. 2020;22:317–24.

Article PubMed Google Scholar

Iregbu K, Nwajiobi-Princewill P, Medugu N, Umeokonkwo C, Uwaezuoke N, Peter Y, et al. Antimicrobial stewardship implementation in Nigerian hospitals: gaps and challenges. Afr J Clin Exper Microbiol. 2021;22:60–6.

Fishman N. Policy statement on amtimicrobial stewardship by the Society for Healthcare Epidemiology of America (SHEA), the Infectious Diseases Society of America (IDSA), and the Pediatric Diseases Society (PIDS). Infect Control Hosp Epidemiol. 2012;33:322–7.

Antimicrobial stewardship: systems and processes for effective antimicrobial medicine use. National Institute of Health and Care Excellence. 2015. https://www.nice.org.uk/guidance/ng15/resources/antimicrobial-stewardship-systems-and-processes-for-effective-antimicrobial-medicine-use-pdf-1837273110469 . Accessed January 17, 2024.

Global action plan on antimicrobial resistance. World Health Organisation. 2015. https://apps.who.int/iris/bitstream/handle/10665/193736/9789241509763_eng.pdf?sequence=1 Accessed January 17, 2024.

Tegagn GT, Yadesa TM, Ahmed Y. Knowledge, attitudes and practices of healthcare professionals towards antimicrobial stewardship and their predictors in Fitche Hospital. J Bioanal Biomed. 2017;9:091–7.

Labi A, Obeng-Nkrumah N, Bjerrum S, Adu Aryee NA, Ofori-Adjei YA, Yawson AE, Newman MJ. Physicians’ knowledge, attitudes, and perceptions concerning antibiotic resistance: a survey in a Ghanaian tertiary care hospital. BMC Health Serv Res. 2018;18:126.

Al-Halawa D, Abu Seir R, Qasrawi R. Antibiotic resistance knowledge, attitudes, and practices among pharmacists: a cross-sectional study in West Bank, Palestine. J Environ Public Health. 2019. https://doi.org/10.1155/2023/2294048 .

Tembo N, Mudenda S, Banda M, Chileshe M, Matafwali S. Knowledge, attitudes and practices on antimicrobial resistance among pharmacy personnel and nurses at a tertiary hospital in Ndola, Zambia: implications for antimicrobial stewardship programmes. JAC Antimicrob Resist. 2022. https://doi.org/10.1093/jacamr/dlac107 .

Sefah I, Chetty S, Yamoah P, Meyer JC, Chigome A, Godman B, Bangalee V. A Multicenter cross-sectional survey of knowledge, attitude, and practices of healthcare professionals towards antimicrobial stewardship in Ghana: findings and implications. Antibiotics. 2023;12:1497.

Carter E, Greendyke WG, Furuya E, Srinivasan A, Shelley A, Bothra A, et al. Exploring the nurses’ role in antibiotic stewardship: a multisite qualitative study of nurses and infection preventionists. Am J Infect Control. 2018;46:492–7.

Huizen P, Kuhn L, Russo PL, Connell CJ. The nurses’ role in antimicrobial stewardship: a scoping review. Int J Nurs Stud. 2021;113:103772.

Davey K, Aveyard H. Nurses’ perceptions of their role in antimicrobial stewardship within the hospital environment. An integrative literature review. J Clin Nurs. 2022;31:3011–20.

Castro-Sánchez E, Gilchrist M, Ahmad R, Courtenay M, Bosanquet J, Holmes AH. Nurse roles in antimicrobial stewardship: lessons from public sectors models of acute care service delivery in the United Kingdom. Antimicrob Resist Infect Control. 2019;8:162.

Merrill K, Hanson SF, Sumner S, Vento T, Veillette J, Webb B. Antimicrobial stewardship: staff nurse knowledge and attitudes. Am J Infect Control. 2019;47:1219–24.

Ju J, Han K, Ryu J, Cho H. Nurses’ attitudes toward antimicrobial stewardship in South Korea. J Hosp Infect. 2022;129:162–70.

Balliram R, Sibanda W, Essack SY. The knowledge, attitudes and practices of doctors, pharmacists and nurses on antimicrobials, antimicrobial resistance and antimicrobial stewardship in South Africa. S Afr J Infect Dis. 202110.4102/ sajid.v36i1.262.

Keijsers CJPW, Brouwers JRBJ, Wildt DJ, Custers EJF, Cate OT, Hazen ACM, et al. A comparison of medical and pharmacy students’ knowledge and skills of pharmacology and pharmacotherapy. Br J Clin Pharmacol. 2014;78(4):781–8.

Harrington AR, Warholak TL, Hines LE, Taylor AM, Sherill D, Malone DC. Healthcare professional students’ knowledge of drug-drug interactions. Am J Pharm Educ. 2011;75:199. https://doi.org/10.5688/ajpe7510199 .

Ubaka CM, Schellack N, Nwomeh B, Goff DA. Antimicrobial resistance and stewardship knowledge and perception among medical and pharmacy students in Nigeria. Open Forum Infect Dis. 2019. https://doi.org/10.1093/ofid/ofz360.1703 .

Davey P, Brown E, Charani E, Fenelon L, Gould IM, Holmes A, et al. Interventions to improve antibiotic prescribing practices for hospital inpatients. Cochrane Database Syst Rev. 2017. https://doi.org/10.1002/14651858.CD003543.pub4 .

MacDougall C, Polk RE. Antimicrobial stewardship programs in health care systems. Clin Microbiol Rev. 2005;18:638–56.

Dellit T, Owens R, McGowan J, Gerding D, Weinstein R, Burke J, et al. Infectious Diseases Society of America and the Society for Healthcare Epidemiology of America guidelines for developing an institutional program to enhance antimicrobial stewardship. Clin Infect Dis. 2007;44:159–77.

Download references

Acknowledgements

The authors are grateful to all healthcare professionals who participated in the study.

No funds, grants, or other support was received for conducting this study.

Author information

Authors and affiliations.

Department of Clinical Pharmacy and Biopharmacy, Faculty of Pharmacy, University of Uyo, Uyo, 520271, Akwa Ibom State, Nigeria

Mary R. Akpan, Idongesit L. Jackson, Unyime I. Eshiet & Sediong A. Mfon

Pharmacy Department, University of Uyo Teaching Hospital, Uyo, Akwa Ibom State, Nigeria

Ekpema A. Abasiattai

You can also search for this author in PubMed Google Scholar

Contributions

MA conceptualised the study. All authors contributed to methods design and ethics processes. Data collection: SM; Data analysis: MA, IJ & SM; Writing of original draft: MA. All authors reviewed, edited and approved the final manuscript.

Corresponding author

Correspondence to Mary R. Akpan .

Ethics declarations

Ethics approval and consent to participate.

Approval to conduct the study was obtained from the Health Research Ethics Committees of the Akwa Ibom State Ministry of Health (AKHREC/01/08/23/169; 07/09/2023) and the University of Uyo Teaching hospital (UUTH/AD/S/96/VOLXXI/776; 21/08/2023). Informed consent to participate in the survey was sought in the questionnaire; participants were required to check a box to consent they agreed to take part in the study.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/ .

Reprints and permissions

About this article

Cite this article.

Akpan, M.R., Jackson, I.L., Eshiet, U.I. et al. Knowledge of antimicrobial stewardship and the Access, Watch and Reserve (AWaRe) classification of antibiotics among frontline healthcare professionals in Akwa Ibom State, Nigeria: a cross-sectional study. BMC Health Serv Res 24 , 1014 (2024). https://doi.org/10.1186/s12913-024-11428-8

Download citation

Received : 10 June 2024

Accepted : 12 August 2024

Published : 02 September 2024

DOI : https://doi.org/10.1186/s12913-024-11428-8

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Antibiotics
Healthcare professionals

BMC Health Services Research

ISSN: 1472-6963

General enquiries: [email protected]

Office of the CIO

Guidelines for data classification.

The purpose of this guideline is to establish a framework for classifying institutional data based on its level of sensitivity, value, and criticality to the university as required by the university's Information Security Policy. Classification of data will aid in determining baseline security controls for the protection of data.

This policy applies to all faculty, staff, students, and third-party agents of the university and any other university affiliate authorized to access institutional data. In particular, this guideline applies to those who are responsible for classifying and protecting institutional data, as defined by Information Security Roles and Responsibilities .

Note : This Guideline applies to all operational and research data.

Definitions

The definitions below are for use within the Guidelines for Data Classification. An affiliate is anyone associated with the university, including students, staff, faculty, emeritus faculty, and any sponsored guests. Most individuals affiliated with the university have an Andrew userID.

Confidential data is a generalized term typically representing data classified as restricted according to the data classification scheme defined in this guideline. This term is often used interchangeably with sensitive data.

A data steward is a senior-level employee of the university who oversees the lifecycle of one or more sets of institutional data. See the Information Security Roles and Responsibilities for more information.

Institutional data is defined as all data owned or licensed by the university.

Non-public information is defined as any information that is classified as private or restricted information according to the data classification scheme defined in this guideline.

Sensitive data is a generalized term typically representing data classified as restricted according to the data classification scheme defined in this guideline. This term is often used interchangeably with confidential data.

Data Classification

Data classification, in the context of information security, is the classification of data based on its level of sensitivity and the impact to the university should that data be disclosed, altered, or destroyed without authorization. Data classification helps determine what baseline security controls are appropriate for safeguarding that data. All institutional data should be classified into one of four sensitivity levels or classifications:

Classification
	Restricted-Specific	Data that is classified as restricted but also has additional requirements for protection based on sponsors, contracts, regulations, and/or data use agreements.	Health or credit card information
	Restricted	Data should be classified as restricted when the unauthorized disclosure, alteration, or destruction of that data could cause a significant level of risk to the University or its affiliates. Examples of restricted data include data protected by state or federal privacy regulations and data protected by confidentiality agreements. The highest level of security controls should be applied to restricted data.	Social security numbers
	Private	Data should be classified as private when the unauthorized disclosure, alteration, or destruction of that data could result in a moderate level of risk to the university or its affiliates. By default, all institutional data that is not explicitly classified as restricted or public should be treated as private. A reasonable level of security controls should be applied to private data.	Home addresses
	Public	Data should be classified as public when the unauthorized disclosure, alteration, or destruction of that data would result in little or no risk to the university and its affiliates. Examples of public data include press releases, course information, and research publications. While little or no controls are required to protect the confidentiality of public data, some control is required to prevent unauthorized modification or destruction of public data.	Course schedule

Classification of data should be performed by an appropriate data steward. Data stewards are senior-level university employees who govern the lifecycle of one or more sets of institutional data. See Information Security Roles and Responsibilities for more information on the data steward role and associated responsibilities.

Visit the Data Classification Workflow for a process on how to classify data.

Data Collections

Data stewards may wish to assign a single classification to a collection of data that is common in purpose or function. When classifying a data collection, the most restrictive classification of any of the individual data elements should be used. For example, if a data collection consists of a student's name, CMU email address, and social security number, the data collection should be classified as restricted even though the student's name and CMU email address may be considered public information.

Reclassification

Periodically, it is important to reevaluate the classification of institutional data to ensure the assigned classification is still appropriate based on changes to legal and contractual obligations as well as changes in the use of the data or its value to the university. This evaluation should be conducted by the appropriate data steward. Conducting an evaluation on an annual basis is encouraged; however, the data steward should determine what frequency is most appropriate based on available resources. If a data steward determines that the classification of a certain data set has changed, an analysis of security controls should be performed to determine whether existing controls are consistent with the new classification. If gaps are found in existing security controls, they should be corrected in a timely manner, commensurate with the level of risk presented by the gaps.

Calculating Classification

The goal of information security, as stated in the university's Information Security Policy, is to protect the confidentiality, integrity, and availability of institutional data. Data classification reflects the level of impact to the university if confidentiality, integrity, or availability is compromised.

Unfortunately, there is no perfect quantitative system for calculating the classification of a particular data element. In some situations, the appropriate classification may be more obvious, such as when federal laws require the university to protect certain types of data (e.g., personally identifiable information). If the appropriate classification is not inherently obvious, consider each security objective using the following table as a guide. It is an excerpt from Federal Information Processing Standards (FIPS) publication 199 , published by the National Institute of Standards and Technology, which discusses the categorization of information and information systems.



Preserving authorized restrictions on information access and disclosure, including means for protecting personal privacy and proprietary information.	The unauthorized disclosure of information could be expected to have a adverse effect on organizational operations, organizational assets, or individuals.	The unauthorized disclosure of information could be expected to have a adverse effect on organizational operations, organizational assets, or individuals.	The unauthorized disclosure of information could be expected to have a adverse effect on organizational operations, organizational assets, or individuals.
Guarding against improper information modification or destruction includes ensuring information non-repudiation and authenticity.	The unauthorized modification or destruction of information could be expected to have a adverse effect on organizational operations, organizational assets, or individuals.	The unauthorized modification or destruction of information could be expected to have a adverse effect on organizational operations, organizational assets, or individuals.	The unauthorized modification or destruction of information could be expected to have a adverse effect on organizational operations, organizational assets, or individuals.
Ensuring timely and reliable access to and use of information.	The disruption of access to or use of information or an information system could be expected to have a adverse effect on organizational operations, organizational assets, or individuals.	The disruption of access to or use of information or an information system could be expected to have a adverse effect on organizational operations, organizational assets, or individuals.	The disruption of access to or use of information or an information system could be expected to have a adverse effect on organizational operations, organizational assets, or individuals.

As the total potential impact on the university increases from low to high, data classification should become more restrictive, moving from public to restricted . If an appropriate classification is still unclear after considering these points, contact the Information Security Office for assistance.

Appendix A: Predefined Types of Restricted Information

The Information Security Office and the Office of General Counsel have defined several types of Restricted data based on state and federal regulatory requirements. This list does not encompass all types of restricted data. Predefined types of restricted information are defined as follows:


	An Authentication Verifier is a piece of information that is held in confidence by an individual and used to prove that the person is who they say they are. In some instances, an Authentication Verifier may be shared amongst a small group of individuals. An Authentication Verifier may also be used to prove the identity of a system or service. Examples include, but are not limited to:

	See the University's .

	EPHI is defined as any Protected Health Information (PHI) that is stored in or transmitted by electronic media. For the purpose of this definition, electronic media includes:

	Export Controlled Materials are defined as any information or materials that are subject to the United States export control regulations, including, but not limited to, the Export Administration Regulations (EAR) published by the US Department of Commerce and the International Traffic in Arms Regulations (ITAR) published by the US Department of State. See the for more information.

	FTI is defined as any return, return information, or taxpayer return information that is entrusted to the University by the Internal Revenue Services. See for more information.

	Payment card information is defined as a credit card number (also referred to as a primary account number or PAN) in combination with one or more of the following data elements: Payment Card Information is also governed by the University's (login required).

	Personally Identifiable Education Records are defined as any Education Records that contain one or more of the following personal identifiers: See Carnegie Mellon's for more information on what constitutes an Education Record.

	For the purpose of meeting security breach notification requirements, PII is defined as a person’s first name or first initial and last name in combination with one or more of the following data elements:

	PHI is defined as individually identifiable health information transmitted by electronic media, maintained in electronic media, or transmitted or maintained in any other form or medium by a Covered Component, as defined in Carnegie Mellon’s . PHI is considered individually identifiable if it contains one or more of the following identifiers: Per Carnegie Mellon's , PHI does not include education records or treatment records covered by the Family Educational Rights and Privacy Act or employment records held by the University in its role as an employer.

	Controlled Technical Information means technical information with military or space applications that is subject to controls on the access, use, reproduction, modification, performance, display, release, disclosure, or dissemination per .

	Documents and data labeled or marked For Official Use Only are a pre-cursor of as defined by the .

	The EU’s General Data Protection Regulation (GDPR) defines personal data as any information that can identify a natural person, directly or indirectly, by reference to an identifier, including: Any personal data that is collected from individuals in European Economic Area (EEA) countries is subject to GDPR. For questions, send an email to .

	, as defined by is a designation from the US government for information that must be protected according to specific requirements (see ). CUI is an umbrella term for multiple other data types, such as , For , and information. Personally Identifiable Information can also be CUI when given to the University as part of a Federal government contract or sub-contract.

Data Classification Workflow [pdf]
Data Classification Workflow [text version]
Data Stewardship Council
Information Security Office
Roles and Responsiblities

Revision History


1.0	11/16/22	Guideline moved from the ISO site.
2.0	4/14/23	Guideline was updated and approved by the Data Stewardship Council.

This week: the arXiv Accessibility Forum

Help | Advanced Search

Computer Science > Computation and Language

Title: modeling text-label alignment for hierarchical text classification.

Abstract: Hierarchical Text Classification (HTC) aims to categorize text data based on a structured label hierarchy, resulting in predicted labels forming a sub-hierarchy tree. The semantics of the text should align with the semantics of the labels in this sub-hierarchy. With the sub-hierarchy changing for each sample, the dynamic nature of text-label alignment poses challenges for existing methods, which typically process text and labels independently. To overcome this limitation, we propose a Text-Label Alignment (TLA) loss specifically designed to model the alignment between text and labels. We obtain a set of negative labels for a given text and its positive label set. By leveraging contrastive learning, the TLA loss pulls the text closer to its positive label and pushes it away from its negative label in the embedding space. This process aligns text representations with related labels while distancing them from unrelated ones. Building upon this framework, we introduce the Hierarchical Text-Label Alignment (HTLA) model, which leverages BERT as the text encoder and GPTrans as the graph encoder and integrates text-label embeddings to generate hierarchy-aware representations. Experimental results on benchmark datasets and comparison with existing baselines demonstrate the effectiveness of HTLA for HTC.

Comments:	Accepted in ECML-PKDD 2024 Research Track
Subjects:	Computation and Language (cs.CL)
Cite as:	[cs.CL]
	(or [cs.CL] for this version)
	Focus to learn more arXiv-issued DOI via DataCite
:	Focus to learn more DOI(s) linking to related resources

Submission history

Access paper:.

HTML (experimental)
Other Formats

References & Citations

Google Scholar
Semantic Scholar

BibTeX formatted citation

Bibliographic and Citation Tools

Code, data and media associated with this article, recommenders and search tools.

Institution

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

IMAGES

(PDF) Research Paper Classification using Supervised Machine Learning
(PDF) Text Classification of Technical Papers Based on Text Segmentation
General flow chart of text classification algorithm. Text...
PPT
Text classification process
Learn How to Write a Classification Essay with Our Checklist

VIDEO

Guidance on the classification of research, article format, and the process of writing an article
AI Revolutionizing Historical Research
Types of Research Papers
Text to handwriting converter pdf and image online
Lecture-2 || Classification of Research || Research Aptitude || UGC NET || Paper-1
Data Preparation

COMMENTS

Deep Learning Based Text Classification: A Comprehensive Review
In this paper, we provide a comprehensive review of more than 150 deep learning based models for text classification developed in recent years, and discuss their technical contributions, similarities, and strengths. We also provide a summary of more than 40 popular datasets widely used for text classification.
Text Classification
1169 papers with code • 92 benchmarks • 145 datasets. Text Classification is the task of assigning a sentence or document an appropriate category. The categories depend on the chosen dataset and can range from topics. Text Classification problems include emotion classification, news classification, citation intent classification, among others.
A Survey on Text Classification: From Traditional to Deep Learning
The AAPD is a large dataset in the computer science field for the multi-label text classification from website 1. It has 55,840 papers, including the abstract and the corresponding subjects with 54 labels in total. The aim is to predict the corresponding subjects of each paper according to the abstract. Patent Dataset.
Deep Learning--based Text Classification: A Comprehensive Review
In Proceedings of the 40th International ACM Conference on Research and Development in Information Retrieval (SIGIR'17). Digital Library. Google Scholar ... it is a difficult classification task for short text classification. In this paper, a short text classification framework based on Siamese CNNs and few-shot learning is proposed. The ...
A Survey on Text Classification: From Traditional to Deep Learning
Text classification is the most fundamental and essential task in natural language processing. The last decade has seen a surge of research in this area due to the unprecedented success of deep learning. Numerous methods, datasets, and evaluation metrics have been proposed in the literature, raising the need for a comprehensive and updated survey.
Efficient English text classification using selected Machine Learning
Abstract. Text classification (TC) is an approach used for the classification of any kind of documents for the target category or out. In this paper, we implemented the Support Vector Machines (SVM) model in classifying English text and documents. Here we did two analytical experiments to check the selected classifiers using English documents.
Text Classification: A Review, Empirical, and Experimental Evaluation
The explosive and widespread growth of data necessitates the use of text classification to extract crucial information from vast amounts of data. Consequently, there has been a surge of research in both classical and deep learning text classification methods. Despite the numerous methods proposed in the literature, there is still a pressing need for a comprehensive and up-to-date survey ...
A Survey on Text Classification: From Traditional to Deep Learning
Text classification is the most fundamental and essential task in natural language processing. The last decade has seen a surge of research in this area due to the unprecedented success of deep learning. Numerous methods, datasets, and evaluation metrics have been proposed in the literature, raising the need for a comprehensive and updated survey.
Text Classification Using Deep Learning Methods
Text classification is a fundamental task in multiple practical scenarios of natural language processing (NLP). During the last few decades, many text classification methods based on deep learning (DL) models have been proposed and adopted in various fields. This article provides an overview description of the mainstream deep learning approaches that are applied in text classification in ...
Research on Text Classification Based on CNN and LSTM
With the rapid development of deep learning technology, CNN and LSTM have become two of the most popular neural networks. This paper combines CNN and LSTM or its variant and makes a slight change. It proposes a text classification model named NA-CNN-LSTM or NA-CNN-COIF-LSTM, which has no activation function in CNN. The experimental results on the subjective and objective text categorization ...
The Research Trends of Text Classification Studies (2000-2020): A
Text Classification (TC), also known as Document Classification or Text Categorization, is the process of assigning several predefined categories to a set of texts, often based on its content (Jindal et al., 2015; Wang & Deng, 2017). With the advent of the era of big data, the enormous quantity and diversity of digital documents have made it ...
Text Classification Using Deep Learning: A Survey
In this paper [], authors have given an excellent introduction to text classification.The paper is very beginner-friendly and has explained almost every text classification technique from basic linear classification models to advanced deep learning models, from supervised learning models to unsupervised learning models, and has also explained pros and cons of every technique.
Text Classification Using Machine Learning Techniques
This paper illustrates the text classification process using machine learning techniques. The. references cited cover the major theoretical issues and gui de the researcher to interesting research ...
Improving text classification through pre-attention mechanism-derived
Text classification is a crucial task in the field of natural language processing (NLP), which is relevant for many real-world applications, including file classification, web search, sentiment analysis, and email categorization [1, 2].Numerous studies on text classification have been conducted [].In the conventional text classification approach, a bag of words is a well-liked and typical way ...
Text Classification Using Machine Learning and Deep Learning Models
With the expanding measure of information and requirement for precision or accuracy automation process is required for the text classification. Another attractive research opportunity is constructing complex "text data models using Deep learning systems" which have the capability to carry out intricate NLP tasks with semantic requirements.
[1904.08067] Text Classification Algorithms: A Survey
In this paper, a brief overview of text classification algorithms is discussed. This overview covers different text feature extractions, dimensionality reduction methods, existing algorithms and techniques, and evaluations methods. Finally, the limitations of each technique and their application in the real-world problem are discussed. Subjects:
10 Must-Read Papers on Text Classification
If you work in this field, keeping up to date with all the novel innovations is essential. So, let's look at 10 must-read articles and research papers on text classification. 1. "The impact of preprocessing on text classification". Authors: Alper Kursay Uysal and Serkan Gunal.
Text Classification Techniques: A Literature Review
This paper states the strengths, limitations and current research trends in text classificati on in an a d-. vanc ed field like AI. The knowledge about text classification is crucial for data ...
Full article: A text classification method based on LSTM and graph
Text classification is a popular research topic in the natural language processing. Recently solving text classification problems with graph neural network (GNN) has received increasing attention. ... The research contribution of this paper has three main aspects. Instead of building one text graph for all documents (including test set), our ...
The Research Trends of Text Classification Studies (2000-2020): A
Text Classification (TC) is the process of assigning several different categories to a set of texts. This study aims to evaluate the state of the arts of TC studies. Firstly, TC-related publications indexed in Web of Science were selected as data. In total, 3,121 TC-related publications were published in 760 journals between 2000 and 2020.
PDF TEXT CLASSFICATION USING CNN AND CNN-LSTM
In this paper, Text classification is carried out by using a deep learning model that is CNN and a hybrid model using CNN & LSTM and compare the performance of two models. In[1] Classical text classification research focuses on three main areas: feature enginee ring, attributes selection, and the application of various ML algorithms. ...
(PDF) A Study of Text Classification Natural Language Processing
Text Classification process consists of various sub phases, each of which has its own importance and. need, as shown in figure 1. Text Classifier, in general, consists of six basic sub parts: Data ...
Deep Learning Based Text Classification: A Comprehensive Review
Sentiment Analysis. Sentiment analysis is a popular branch of text classification, which aims to analyze people's opinions in textual data (such as product reviews, movie reviews, and tweets), and extract their polarity and viewpoint. Sentiment classification can be either a binary or a multi-class problem.
Using Large Language Models to Extract and Analyze Medical Text for
Utilizing both real and generated data, this work serves as a prototype for future research involving authentic clinical datasets. The primary aim is to propose a robust methodology and algorithm for employing LLMs in this domain rather than delivering an immediate, ready-to-use classification tool.
Research on BERT-based deep multilayer fusion Chinese short text
The categorization of brief Chinese texts, a critical area for extracting insights from data with limited information content, presents unique challenges such as limited word count, ambiguity, and non-standardized information. These factors complicate the extraction and representation of textual features. This study introduces the BERT-based BRLC (BERT Recurrent Layer Composition) model ...
Agriculture
As the quality of life rises, the demand for flowers has increased significantly, leading to higher expectations for flower sorting system efficiency and speed. This paper presents a real-time, high-precision end-to-end method, which can complete three key tasks in the sorting system: flower localization, flower classification, and flower grading. In order to improve the challenging maturity ...
[2305.08377] Text Classification via Large Language Models
View a PDF of the paper titled Text Classification via Large Language Models, by Xiaofei Sun and 5 other authors. Despite the remarkable success of large-scale Language Models (LLMs) such as GPT-3, their performances still significantly underperform fine-tuned models in the task of text classification. This is due to (1) the lack of reasoning ...
Knowledge of antimicrobial stewardship and the Access, Watch and
Background Antimicrobial stewardship (AMS) aims to improve antibiotic use while reducing resistance and its consequences. There is a paucity of data on the availability of AMS programmes in southern Nigeria. Further, there is no data on Nigerian healthcare professionals' knowledge of the WHO 'Access, Watch and Reserve' (AWaRe) classification of antibiotics. This study sought to assess ...
Data Classification
Note: This Guideline applies to all operational and research data. Definitions. The definitions below are for use within the Guidelines for Data Classification. An affiliate is anyone associated with the university, including students, staff, faculty, emeritus faculty, and any sponsored guests. Most individuals affiliated with the university ...
Modeling Text-Label Alignment for Hierarchical Text Classification
Hierarchical Text Classification (HTC) aims to categorize text data based on a structured label hierarchy, resulting in predicted labels forming a sub-hierarchy tree. The semantics of the text should align with the semantics of the labels in this sub-hierarchy. With the sub-hierarchy changing for each sample, the dynamic nature of text-label alignment poses challenges for existing methods ...

Subscribe to the PwC Newsletter

Benchmarks Add a Result

Most implemented papers

Semi-supervised Sequence Learning

Universal Language Model Fine-tuning for Text Classification

Bag of Tricks for Efficient Text Classification

RoBERTa: A Robustly Optimized BERT Pretraining Approach

FastText.zip: Compressing text classification models

Character-level Convolutional Networks for Text Classification

Distributed Representations of Sentences and Documents

Revisiting Semi-Supervised Learning with Graph Embeddings

Universal Sentence Encoder

A Survey on Text Classification: From Traditional to Deep Learning

New Citation Alert!

Information & Contributors

1.1 Major Differences and Contributions

1.2 Organization of the Survey

2.1.1 PGM-based Methods.

2.1.2 KNN-based Methods.

2.1.3 SVM-based Methods.

2.1.5 Integration-based Methods.

2.2.2 MLP-based Methods.

2.2.4 CNN-based Methods.

2.2.6 Pre-trained Methods.

2.2.7 GNN-based Methods.

2.2.8 Others.

3.2.1 Single-label Metrics.

5 Future Research Challenges

Index Terms

Recommendations

Chinese text classification by the Naïve Bayes Classifier and the associative classifier with multiple confidence threshold values

Exploring Video Captioning Techniques: A Comprehensive Survey on Deep Learning Methods

Information

Publication History

Funding Sources

Contributors

View options

HTML Format

Login options

Full Access

Share on social media

IEEE Account

Purchase Details

Profile Information

Improving text classification through pre-attention mechanism-derived lexicons

Cite this article

Graphical abstract

Access this article

Similar content being viewed by others

Dual-axial self-attention network for text classification

Word-character attention model for Chinese text classification

CRAN: A Hybrid CNN-RNN Attention-Based Model for Text Classification

Data Availability and Access

Author information

Contributions

Corresponding author

Ethics declarations

Ethics Approval

Additional information

Rights and permissions

About this article

Share this article

Article Menu

JSmol Viewer

Share and Cite

Article Metrics

Knowledge of antimicrobial stewardship and the Access, Watch and Reserve (AWaRe) classification of antibiotics among frontline healthcare professionals in Akwa Ibom State, Nigeria: a cross-sectional study

Conclusions

Introduction

Study design, population and setting

Survey instrument and data collection

Statistical analysis

Ethical considerations

Participants’ characteristics

Knowledge of antimicrobial stewardship, antimicrobial stewardship availability and AWaRe classification among healthcare professionals in participating hospitals

Knowledge of the AWaRe classification of antibiotics among healthcare professionals

Effects of participants’ characteristics on knowledge of antimicrobial stewardship

Effects of participants’ characteristics on knowledge of the AWaRe classification of antibiotics

Limitations

Data availability