Natural language content evaluation system for multiclass detection of hate speech in tweets using transformers
In natural language processing, accurate categorization of tweets, including detecting hate speech, plays a pivotal role in efficient information organization and analysis. This paper presents a Natural Language Contents Evaluation System specifically tailored for multi-class tweet categorization, f...
- Autores:
-
Marrugo-Tobón, Duván Andres
Martinez-Santos, Juan Carlos
Puertas, Edwin
- Tipo de recurso:
- Fecha de publicación:
- 2023
- Institución:
- Universidad Tecnológica de Bolívar
- Repositorio:
- Repositorio Institucional UTB
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.utb.edu.co:20.500.12585/12581
- Acceso en línea:
- https://hdl.handle.net/20.500.12585/12581
https://ceur-ws.org/Vol-3496/homomex-paper4.pdf
- Palabra clave:
- BERT
DistilBERT
Feature extraction
Hate speech detection
Natural language processing
Transformers
Tweet categorization
LEMB
- Rights
- openAccess
- License
- http://creativecommons.org/licenses/by-nc-nd/4.0/
| id |
UTB2_45f167fe682707cafb0a211c3f31369c |
|---|---|
| oai_identifier_str |
oai:repositorio.utb.edu.co:20.500.12585/12581 |
| network_acronym_str |
UTB2 |
| network_name_str |
Repositorio Institucional UTB |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
Natural language content evaluation system for multiclass detection of hate speech in tweets using transformers |
| title |
Natural language content evaluation system for multiclass detection of hate speech in tweets using transformers |
| spellingShingle |
Natural language content evaluation system for multiclass detection of hate speech in tweets using transformers BERT DistilBERT Feature extraction Hate speech detection Natural language processing Transformers Tweet categorization LEMB |
| title_short |
Natural language content evaluation system for multiclass detection of hate speech in tweets using transformers |
| title_full |
Natural language content evaluation system for multiclass detection of hate speech in tweets using transformers |
| title_fullStr |
Natural language content evaluation system for multiclass detection of hate speech in tweets using transformers |
| title_full_unstemmed |
Natural language content evaluation system for multiclass detection of hate speech in tweets using transformers |
| title_sort |
Natural language content evaluation system for multiclass detection of hate speech in tweets using transformers |
| dc.creator.fl_str_mv |
Marrugo-Tobón, Duván Andres Martinez-Santos, Juan Carlos Puertas, Edwin |
| dc.contributor.author.none.fl_str_mv |
Marrugo-Tobón, Duván Andres Martinez-Santos, Juan Carlos Puertas, Edwin |
| dc.subject.keywords.spa.fl_str_mv |
BERT DistilBERT Feature extraction Hate speech detection Natural language processing Transformers Tweet categorization |
| topic |
BERT DistilBERT Feature extraction Hate speech detection Natural language processing Transformers Tweet categorization LEMB |
| dc.subject.armarc.none.fl_str_mv |
LEMB |
| description |
In natural language processing, accurate categorization of tweets, including detecting hate speech, plays a pivotal role in efficient information organization and analysis. This paper presents a Natural Language Contents Evaluation System specifically tailored for multi-class tweet categorization, focusing on hate speech detection. Our system enhances classification accuracy and efficiency by harnessing the power of Transformers, namely BERT and DistilBERT. By leveraging feature extraction techniques, we capture pertinent information from tweets, enabling practical analysis, categorization, and identification of hate speech instances. During training, we also tackle imbalanced corpora by employing techniques to ensure fair representation of different tweet categories, including hate speech. Our system achieves impressive accuracy through extensive training of 95%, showcasing Transformers' effectiveness in comprehending and categorizing tweets, including identifying hate speech. Furthermore, our system maintains a good accuracy during testing of 83%, highlighting the robustness and generalizability of the trained models for hate speech detection. This system contributes to advancing automated tweet categorization, specifically in hate speech detection, providing a reliable and efficient solution for organizing and analyzing diverse tweet datasets. |
| publishDate |
2023 |
| dc.date.accessioned.none.fl_str_mv |
2023-12-05T18:16:47Z |
| dc.date.available.none.fl_str_mv |
2023-12-05T18:16:47Z |
| dc.date.issued.none.fl_str_mv |
2023-12-05 |
| dc.date.submitted.none.fl_str_mv |
2023-12-05 |
| dc.type.coarversion.fl_str_mv |
http://purl.org/coar/version/c_b1a7d7d4d402bcce http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| dc.type.coar.fl_str_mv |
http://purl.org/coar/resource_type/c_2df8fbb1 |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/article |
| dc.type.spa.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_6501 |
| dc.identifier.citation.spa.fl_str_mv |
Marrugo-Tobón, D., Martınez-Santos, J., & Puerta, E. (2023). Natural language content evaluation system for multiclass detection of hate speech in tweets using transformers. In Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2023). |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/20.500.12585/12581 |
| dc.identifier.url.none.fl_str_mv |
https://ceur-ws.org/Vol-3496/homomex-paper4.pdf |
| dc.identifier.instname.spa.fl_str_mv |
Universidad Tecnológica de Bolívar |
| dc.identifier.reponame.spa.fl_str_mv |
Repositorio Universidad Tecnológica de Bolívar |
| identifier_str_mv |
Marrugo-Tobón, D., Martınez-Santos, J., & Puerta, E. (2023). Natural language content evaluation system for multiclass detection of hate speech in tweets using transformers. In Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2023). Universidad Tecnológica de Bolívar Repositorio Universidad Tecnológica de Bolívar |
| url |
https://hdl.handle.net/20.500.12585/12581 https://ceur-ws.org/Vol-3496/homomex-paper4.pdf |
| dc.language.iso.spa.fl_str_mv |
eng |
| language |
eng |
| dc.rights.coar.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
| dc.rights.uri.*.fl_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
| dc.rights.cc.*.fl_str_mv |
Attribution-NonCommercial-NoDerivatives 4.0 Internacional |
| rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-nd/4.0/ Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://purl.org/coar/access_right/c_abf2 |
| eu_rights_str_mv |
openAccess |
| dc.format.extent.none.fl_str_mv |
12 páginas |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.publisher.place.spa.fl_str_mv |
Cartagena de Indias |
| dc.publisher.sede.spa.fl_str_mv |
Campus Tecnológico |
| dc.publisher.discipline.spa.fl_str_mv |
Maestría en Ingeniería |
| dc.source.spa.fl_str_mv |
Iberian Languages Evaluation Forum |
| institution |
Universidad Tecnológica de Bolívar |
| bitstream.url.fl_str_mv |
https://repositorio.utb.edu.co/bitstream/20.500.12585/12581/1/homomex-paper4.pdf https://repositorio.utb.edu.co/bitstream/20.500.12585/12581/2/license_rdf https://repositorio.utb.edu.co/bitstream/20.500.12585/12581/3/license.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12581/4/homomex-paper4.pdf.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12581/5/homomex-paper4.pdf.jpg |
| bitstream.checksum.fl_str_mv |
c8cd0896269b2d02ad0cc83ebd4823b9 4460e5956bc1d1639be9ae6146a50347 e20ad307a1c5f3f25af9304a7a7c86b6 5c2d10258780db1bee1e698cc31cb1a8 faff5e7ad5dffeea8bf142f2311b3edd |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional UTB |
| repository.mail.fl_str_mv |
repositorioutb@utb.edu.co |
| _version_ |
1808397607325663232 |
| spelling |
Marrugo-Tobón, Duván Andresad972207-0602-4d70-b9c2-5aa4f18f527aMartinez-Santos, Juan Carlos5c958644-c78d-401d-8ba9-bbd39fe77318Puertas, Edwin5a1b1566-e112-43dc-8ac7-310ea9af8f052023-12-05T18:16:47Z2023-12-05T18:16:47Z2023-12-052023-12-05Marrugo-Tobón, D., Martınez-Santos, J., & Puerta, E. (2023). Natural language content evaluation system for multiclass detection of hate speech in tweets using transformers. In Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2023).https://hdl.handle.net/20.500.12585/12581https://ceur-ws.org/Vol-3496/homomex-paper4.pdfUniversidad Tecnológica de BolívarRepositorio Universidad Tecnológica de BolívarIn natural language processing, accurate categorization of tweets, including detecting hate speech, plays a pivotal role in efficient information organization and analysis. This paper presents a Natural Language Contents Evaluation System specifically tailored for multi-class tweet categorization, focusing on hate speech detection. Our system enhances classification accuracy and efficiency by harnessing the power of Transformers, namely BERT and DistilBERT. By leveraging feature extraction techniques, we capture pertinent information from tweets, enabling practical analysis, categorization, and identification of hate speech instances. During training, we also tackle imbalanced corpora by employing techniques to ensure fair representation of different tweet categories, including hate speech. Our system achieves impressive accuracy through extensive training of 95%, showcasing Transformers' effectiveness in comprehending and categorizing tweets, including identifying hate speech. Furthermore, our system maintains a good accuracy during testing of 83%, highlighting the robustness and generalizability of the trained models for hate speech detection. This system contributes to advancing automated tweet categorization, specifically in hate speech detection, providing a reliable and efficient solution for organizing and analyzing diverse tweet datasets.Universidad Tecnología de Bolívar12 páginasapplication/pdfenghttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessAttribution-NonCommercial-NoDerivatives 4.0 Internacionalhttp://purl.org/coar/access_right/c_abf2Iberian Languages Evaluation ForumNatural language content evaluation system for multiclass detection of hate speech in tweets using transformersinfo:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501http://purl.org/coar/version/c_b1a7d7d4d402bccehttp://purl.org/coar/version/c_970fb48d4fbd8a85http://purl.org/coar/resource_type/c_2df8fbb1BERTDistilBERTFeature extractionHate speech detectionNatural language processingTransformersTweet categorizationLEMBCartagena de IndiasCampus TecnológicoMaestría en IngenieríaPúblico generalKim, H., & Jeong, Y. S. (2019). Sentiment classification using convolutional neural networks. Applied Sciences, 9(11), 2347.Galas, M. (2015). Experimental Computational Simulation Environments for Big Data Analytic in Social Sciences. In Handbook of Statistics (Vol. 33, pp. 259-277). Elsevier.Abro, S., Shaikh, S., Khand, Z. H., Zafar, A., Khan, S., & Mujtaba, G. (2020). Automatic hate speech detection using machine learning: A comparative study. International Journal of Advanced Computer Science and Applications, 11(8).Alkomah, F., & Ma, X. (2022). A literature review of textual hate speech detection methods and datasets. Information, 13(6), 273.Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108.Madni, H. A., Umer, M., Abuzinadah, N., Hu, Y. C., Saidani, O., Alsubai, S., ... & Ashraf, I. (2023). Improving Sentiment Prediction of Textual Tweets Using Feature Fusion and Deep Machine Ensemble Model. Electronics, 12(6), 1302.Tan, K. L., Lee, C. P., & Lim, K. M. (2023). A survey of sentiment analysis: Approaches, datasets, and future research. Applied Sciences, 13(7), 4550.Tan, K. L., Lee, C. P., & Lim, K. M. (2023). A survey of sentiment analysis: Approaches, datasets, and future research. Applied Sciences, 13(7), 4550.Severyn, A., & Moschitti, A. (2015, August). Twitter sentiment analysis with deep convolutional neural networks. In Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval (pp. 959-962).Pilar, G. D., Isabel, S. B., Diego, P. M., & Luis, G. A. J. (2023). A novel flexible feature extraction algorithm for Spanish tweet sentiment analysis based on the context of words. Expert Systems with Applications, 212, 118817.Behera, R. K., Jena, M., Rath, S. K., & Misra, S. (2021). Co-LSTM: Convolutional LSTM model for sentiment analysis in social big data. Information Processing & Management, 58(1), 102435.Elreedy, D., & Atiya, A. F. (2019). A comprehensive analysis of synthetic minority oversampling technique (SMOTE) for handling class imbalance. Information Sciences, 505, 32-64.Hussein, A. S., Li, T., Abd Ali, D. M., Bashir, K., & Yohannese, C. W. (2020). A modified adaptive synthetic sampling method for learning imbalanced datasets. In Developments of Artificial Intelligence Technologies in Computation and Robotics: Proceedings of the 14th International FLINS Conference (FLINS 2020) (pp. 76-83).Aloraini, M., Khan, A., Aladhadh, S., Habib, S., Alsharekh, M. F., & Islam, M. (2023). Combining the Transformer and Convolution for Effective Brain Tumor Classification Using MRI Images. Applied Sciences, 13(6), 3680.Jang, B., Kim, M., Harerimana, G., Kang, S. U., & Kim, J. W. (2020). Bi-LSTM model to increase accuracy in text classification: Combining Word2vec CNN and attention mechanism. Applied Sciences, 10(17), 5841.Bel-Enguix, G., Gómez-Adorno, H., Sierra, G., Vásquez, J., Andersen, S. T., & Ojeda-Trueba, S. (2023). Overview of HOMO-MEX at Iberlef 2023: Hate speech detection in Online Messages directed Towards the MEXican Spanish speaking LGBTQ+ population. Procesamiento del lenguaje natural, 71, 361-370.Eler, D. M., Grosa, D., Pola, I., Garcia, R., Correia, R., & Teixeira, J. (2018). Analysis of document pre-processing effects in text and opinion mining. Information, 9(4), 100.Huerta-Velasco, D. A., & Calvo, H. (2022). Verbal Aggressions Detection in Mexican Tweets. Computación y Sistemas, 26(1), 261-269.Silva Barbon, R., & Akabane, A. T. (2022). Towards Transfer Learning Techniques—BERT, DistilBERT, BERTimbau, and DistilBERTimbau for Automatic Text Classification from Different Languages: A Case Study. Sensors, 22(21), 8184.http://purl.org/coar/resource_type/c_6501ORIGINALhomomex-paper4.pdfhomomex-paper4.pdfhomomex-paperapplication/pdf1265269https://repositorio.utb.edu.co/bitstream/20.500.12585/12581/1/homomex-paper4.pdfc8cd0896269b2d02ad0cc83ebd4823b9MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8805https://repositorio.utb.edu.co/bitstream/20.500.12585/12581/2/license_rdf4460e5956bc1d1639be9ae6146a50347MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-83182https://repositorio.utb.edu.co/bitstream/20.500.12585/12581/3/license.txte20ad307a1c5f3f25af9304a7a7c86b6MD53TEXThomomex-paper4.pdf.txthomomex-paper4.pdf.txtExtracted texttext/plain31440https://repositorio.utb.edu.co/bitstream/20.500.12585/12581/4/homomex-paper4.pdf.txt5c2d10258780db1bee1e698cc31cb1a8MD54THUMBNAILhomomex-paper4.pdf.jpghomomex-paper4.pdf.jpgGenerated Thumbnailimage/jpeg5774https://repositorio.utb.edu.co/bitstream/20.500.12585/12581/5/homomex-paper4.pdf.jpgfaff5e7ad5dffeea8bf142f2311b3eddMD5520.500.12585/12581oai:repositorio.utb.edu.co:20.500.12585/125812023-12-06 00:20:48.215Repositorio Institucional UTBrepositorioutb@utb.edu.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 |