Authors : Dr. M. Ayyavaraiah; D. Sreenath

Volume/Issue : Volume 10 - 2025, Issue 6 - June

Google Scholar : https://tinyurl.com/39mnyt2j

DOI : https://doi.org/10.38124/ijisrt/25jun516

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Harmful comments are insulting, aggressive, or irrational and can interfere with online discussions and frequently cause participants to disengage. The widespread issue of cyberbullying and digital harassment undermines open communication by deterring people from expressing opposing perspectives. Numerous websites encounter difficulties sustaining constructive conversations, prompting some to limit or completely remove commenting. This research intends to investigate the prevalence of online abuse and categorize user input through annotated data to effectively recognize toxicity. To tackle this challenge, we will implement numerous Natural Language Processing (NLP) techniques to handle text categorization, assessing their outcomes to identify the most efficient approach for toxic comment identification. Numerous machine learning methods, including SVM, logistic regression, decision tree and deep Learning Techniques, are used to group the abusive words. Our objective is to attain high precision in detecting toxic behaviour, thus motivating organizations to adopt measures that reduce its negative consequences.

Keywords : Harmful Comments, Machine Learning, Toxicity, Insulting, Communication, Deep Learning, Logistic Regression and Naive Bayes.

References :

1. H. M. Saleem, K. P. Dillon, S. Benesch, and D. Ruths, “A Web of Hate: Tackling Hateful Speech in Online Social Spaces,” 2017, [Online]. Available: http://arxiv.org/abs/1709.10159.
2. M. Duggan, “Online harassment 2017,” Pew Res., pp. 1–85, 2017, doi: 202.419.4372.
3. M. A. Walker, P. Anand, J. E. F. Tree, R. Abbott, and J. King, “A corpus for research on deliberation and debate,” Proc. 8th Int. Conf. Lang. Resour. Eval. Lr. 2012, pp. 812–817, 2012.
4. J. Cheng, C. Danescu-Niculescu-Mizel, and J. Leskovec, “Antisocial behaviour in online discussion communities,” Proc. 9th Int. Conf. Web Soc. Media, ICWSM 2015, pp. 61–70, 2015.
5. B. Mathew et al., “Thou shalt not hate: Countering online hate speech,” Proc. 13th Int. Conf. Web Soc. Media, ICWSM 2019, no. August, pp. 369–380, 2019.
6. C. Nobata, J. Tetreault, A. Thomas, Y. Mehdad, and Y. Chang, “Abusive language detection in online user content,” 25th Int. World Wide Web Conf. WWW 2016, pp. 145–153, 2016, Doi: 10.1145/2872427.2883062.
7. E. K. Ikonomakis, S. Kotsiantis, and V. Tampakas, “Text Classification Using Machine Learning Techniques,” no. August, 2005.
8. M. R. Murty, J. V. . Murthy, and P. Reddy P.V.G.D, “ Text Document Classification based on Least Square Support Vector Machines with Singular Value Decomposition,” Int. J. Comput. Appl., vol. 27, no. 7, pp. 21–26, 2011, doi: 10.5120/3312-4540.
9. E. Wulczyn, N. Thain, and L. Dixon, “Ex machina: Personal attacks seen at scale,” 26th Int. World Wide Web Conf. WWW 2017, pp. 1391– 1399, 2017, doi: 10.1145/3038912.3052591.
10. H. Hosseini, S. Kannan, B. Zhang, and R. Poovendran, “Deceiving Google’s Perspective API Built for Detecting Toxic Comments,” 2017, [Online]. Available: http://arxiv.org/abs/1702.08138.