{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T10:40:04Z","timestamp":1776336004810,"version":"3.51.2"},"reference-count":35,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T00:00:00Z","timestamp":1660694400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Explainable artificial intelligence (XAI) characteristics have flexible and multifaceted potential in hate speech detection by deep learning models. Interpreting and explaining decisions made by complex artificial intelligence (AI) models to understand the decision-making process of these model were the aims of this research. As a part of this research study, two datasets were taken to demonstrate hate speech detection using XAI. Data preprocessing was performed to clean data of any inconsistencies, clean the text of the tweets, tokenize and lemmatize the text, etc. Categorical variables were also simplified in order to generate a clean dataset for training purposes. Exploratory data analysis was performed on the datasets to uncover various patterns and insights. Various pre-existing models were applied to the Google Jigsaw dataset such as decision trees, k-nearest neighbors, multinomial na\u00efve Bayes, random forest, logistic regression, and long short-term memory (LSTM), among which LSTM achieved an accuracy of 97.6%. Explainable methods such as LIME (local interpretable model\u2014agnostic explanations) were applied to the HateXplain dataset. Variants of BERT (bidirectional encoder representations from transformers) model such as BERT + ANN (artificial neural network) with an accuracy of 93.55% and BERT + MLP (multilayer perceptron) with an accuracy of 93.67% were created to achieve a good performance in terms of explainability using the ERASER (evaluating rationales and simple English reasoning) benchmark.<\/jats:p>","DOI":"10.3390\/a15080291","type":"journal-article","created":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T21:23:56Z","timestamp":1660771436000},"page":"291","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":75,"title":["Social Media Hate Speech Detection Using Explainable Artificial Intelligence (XAI)"],"prefix":"10.3390","volume":"15","author":[{"given":"Harshkumar","family":"Mehta","sequence":"first","affiliation":[{"name":"School of Engineering and Computer Science, Laurentian University, Sudbury, ON P3E 2C6, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7155-7901","authenticated-orcid":false,"given":"Kalpdrum","family":"Passi","sequence":"additional","affiliation":[{"name":"School of Engineering and Computer Science, Laurentian University, Sudbury, ON P3E 2C6, Canada"}]}],"member":"1968","published-online":{"date-parts":[[2022,8,17]]},"reference":[{"key":"ref_1","unstructured":"Davidson, T., Warmsley, D., Macy, M., and Weber, I. (2022, August 11). Automated Hate Speech Detection and the Problem of Offensive Language. Available online: http:\/\/arxiv.org\/abs\/1703.04009."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhou, Y., Zhu, S., and Xu, H. (2012, January 3\u20135). Detecting offensive language in social media to protect adolescent online safety. Proceedings of the 2012 ASE\/IEEE International Conference on Privacy, Security, Risk and Trust and 2012 ASE\/IEEE International Conference on Social Computing, SocialCom\/PASSAT, Amsterdam, The Netherlands.","DOI":"10.1109\/SocialCom-PASSAT.2012.55"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Balkir, E., Nejadgholi, I., Fraser, K.C., and Kiritchenko, S. (2022). Necessity and sufficiency for explaining text classifiers: A case study in hate speech detection. arXiv.","DOI":"10.18653\/v1\/2022.naacl-main.192"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Chatzakou, D., Kourtellis, N., Blackburn, J., de Cristofaro, E., Stringhini, G., and Vakali, A. (2017). Mean birds: Detecting aggression and bullying on Twitter. WebSci 2017\u2014Proceedings of the 2017 ACM Web Science Conference, Association for Computing Machinery.","DOI":"10.1145\/3091478.3091487"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Founta, A.M., Chatzakou, D., Kourtellis, N., Blackburn, J., Vakali, A., and Leontiadis, I. (2018). A Unified Deep Learning Architecture for Abuse Detection. WebSci 2019\u2014Proceedings of the 11th ACM Conference on Web Science, Association for Computing Machinery.","DOI":"10.1145\/3292522.3326028"},{"key":"ref_6","unstructured":"Lundberg, S.M., and Lee, S.I. (2017). A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Arras, L., Montavon, G., M\u00fcller, K.R., and Samek, W. (2017). Explaining recurrent neural network predictions in sentiment analysis. EMNLP 2017\u20148th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2017\u2014Proceedings of the Workshop, Association for Computational Linguistics.","DOI":"10.18653\/v1\/W17-5221"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Mahajan, A., Shah, D., and Jafar, G. (2021). Explainable AI approach towards toxic comment classification. Emerging Technologies in Data Mining and Information Security, Springer.","DOI":"10.1007\/978-981-33-4367-2_81"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). \u201cWhy Should I Trust You?\u201d: Explaining the Predictions of Any Classifier. Proceedings of the NAACL-HLT 2016\u20142016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Demonstrations Session, San Francisco, CA, USA.","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref_10","unstructured":"Samek, W., Montavon, G., Lapuschkin, S., Anders, C.J., and M\u00fcller, K.-R. (2022, August 11). Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond. Available online: https:\/\/doi.org\/10.48550\/arXiv.2003.07631."},{"key":"ref_11","unstructured":"Doshi-Velez, F., and Kim, B. (2022, January 11). Towards A Rigorous Science of Interpretable Machine Learning. Available online: https:\/\/doi.org\/10.48550\/arXiv.1702.08608."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hind, M., Wei, D., Campbell, M., Codella, N.C.F., Dhurandhar, A., Mojsilovi\u0107, A., Natesan Ramamurthy, K., and Varshney, K.R. (2019). TED: Teaching AI to explain its decisions. AIES 2019. Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society, Association for Computing Machinery.","DOI":"10.1145\/3306618.3314273"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.dsp.2017.10.011","article-title":"Methods for interpreting and understanding deep neural networks","volume":"73","author":"Montavon","year":"2018","journal-title":"Digit. Signal Process."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Gilpin, L.H., Bau, D., Yuan, B.Z., Bajwa, A., Specter, M., and Kagal, L. (2018, January 1\u20133). Explaining explanations: An overview of interpretability of machine learning. Proceedings of the 2018 IEEE 5th International Conference on Data Science and Advanced Analytics, DSAA, Turin, Italy.","DOI":"10.1109\/DSAA.2018.00018"},{"key":"ref_15","unstructured":"Lundberg, S.M., Erion, G., Chen, H., DeGrave, A., Prutkin, J.M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., and Lee, S. (2019). Explainable AI for Trees: From Local Explanations to Global Understanding. arXiv, Available online: http:\/\/arxiv.org\/abs\/1905.04610."},{"key":"ref_16","unstructured":"Nori, H., Jenkins, S., Koch, P., and Caruana, R. (2019). InterpretML: A Unified Framework for Machine Learning Interpretability. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ahmed, U., and Lin, J.C.-W. (2022). Deep Explainable Hate Speech Active Learning on Social-Media Data. IEEE Trans. Comput. Soc. Syst., 1\u201311.","DOI":"10.1109\/TCSS.2022.3165136"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Bennetot","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_19","unstructured":"Das, A., and Rad, P. (2020). Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey. arXiv."},{"key":"ref_20","unstructured":"Kanerva, O. (2022, January 25). Evaluating Explainable AI Models for Convolutional Neural Networks with Proxy Tasks. Available online: https:\/\/www.semanticscholar.org\/paper\/Evaluating-explainable-AI-models-for-convolutional_Kanerva\/d91062a3e13ee034af6807e1819a9ca3051daf13."},{"key":"ref_21","unstructured":"Gohel, P., Singh, P., and Mohanty, M. (2022, January 30). Explainable AI: Current STATUs and Future Directions. Available online: https:\/\/doi.org\/10.1109\/ACCESS.2017."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1109\/MCI.2018.2881645","article-title":"Evolutionary fuzzy systems for explainable artificial intelligence: Why, when, what for, and where to?","volume":"14","author":"Fernandez","year":"2019","journal-title":"IEEE Comput. Intell. Mag."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Clinciu, M.-A., and Hastie, H. (2019). A Survey of Explainable AI Terminology. Proceedings of the 1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence (NL4XAI 2019), Association for Computational Linguistics.","DOI":"10.18653\/v1\/W19-8403"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Hrnjica, B., and Softic, S. (2020). Explainable AI in Manufacturing: A Predictive Maintenance Case Study. IFIP Advances in Information and Communication Technology, 592 IFIP, Springer.","DOI":"10.1007\/978-3-030-57997-5_8"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","article-title":"Explanation in artificial intelligence: Insights from the social sciences","volume":"267","author":"Miller","year":"2019","journal-title":"Artif. Intell."},{"key":"ref_26","unstructured":"Mathew, B., Saha, P., Yimam, S.M., Biemann, C., Goyal, P., and Mukherjee, A. (2020). HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection. arXiv, Available online: http:\/\/arxiv.org\/abs\/2012.10289."},{"key":"ref_27","unstructured":"(2022, April 03). ML|Overview of Data Cleaning. GeeksforGeeks. Available online: https:\/\/www.geeksforgeeks.org\/data-cleansing-introduction\/."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Pearson, R.K. (2018). Exploratory Data Analysis: A First Look. Exploratory Data Analysis Using R, Chapman and Hall\/CRC.","DOI":"10.1201\/9781315382111-3"},{"key":"ref_29","unstructured":"(2022, April 03). Using CountVectorizer to Extracting Features from Text. GeeksforGeeks. Available online: https:\/\/www.geeksforgeeks.org\/using-countvectorizer-to-extracting-features-from-text\/."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Bisong, E. (2019). The Multilayer Perceptron (MLP). Building Machine Learning and Deep Learning Models on Google Cloud Platform, Apress.","DOI":"10.1007\/978-1-4842-4470-8"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Kamath, U., Graham, K.L., and Emara, W. (2022). Bidirectional encoder representations from transformers (BERT). Transformers for Machine Learning, Chapman and Hall\/CRC.","DOI":"10.1201\/9781003170082"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Awal, M.R., Cao, R., Lee, R.K.-W., and Mitrovic, S. (2021). AngryBERT: Joint Learning Target and Emotion for Hate Speech Detection. arXiv, Available online: http:\/\/arxiv.org\/abs\/2103.11800.","DOI":"10.1007\/978-3-030-75762-5_55"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Nair, R., Prasad, V.N.V., Sreenadh, A., and Nair, J.J. (2021, January 21\u201323). Coreference Resolution for Ambiguous Pronoun with BERT and MLP. Proceedings of the 2021 International Conference on Advances in Computing and Communications (ICACC), Kochi, India.","DOI":"10.1109\/ICACC-202152719.2021.9708203"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Biecek, P., and Burzykowski, T. (2021). Local interpretable model-agnostic explanations (LIME). Explanatory Model Analysis, Chapman and Hall\/CRC.","DOI":"10.1201\/9780429027192"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"DeYoung, J., Jain, S., Rajani, N.F., Lehman, E., Xiong, C., Socher, R., and Wallace, B.C. (2020). ERASER: A Benchmark to Evaluate Rationalized NLP Models. arXiv.","DOI":"10.18653\/v1\/2020.acl-main.408"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/15\/8\/291\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:10:57Z","timestamp":1760141457000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/15\/8\/291"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,17]]},"references-count":35,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["a15080291"],"URL":"https:\/\/doi.org\/10.3390\/a15080291","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,17]]}}}