Deep Learning Approach for Multi-label Detection of Abusive Bangla Social Media Comments
Saieef Sunny, Dewan Rezwan Ahmed, Md. Ahashan Habib, Sajida Tajreen Kabir, Md. Abdulla Al Masud, Nafees Mansoor
Conference Paper. 2nd International Conference on Information and Communication Technology, ICICT 2024, pp. 90–94 (2024).
Abstract
This paper presents a multilabel classification model to detect and classify various abuse or bullying content from Bangla social media comments. We utilized an LSTM-based deep learning model to train a classification system using a dataset of 12,557 multilabel comments. The comments were categorized into five categories: Bully, Sexual, Religious, Threat, and Spam. The model achieved an overall accuracy of 93.64% and an AUC of 0.9802. These metrics highlight the model’s effectiveness in identifying and classifying abusive content. The results show that the model is robust and dependable, making it a valuable tool for addressing and mitigating various forms of Bangla text-based abuse. ©2024 IEEE.
Keywords
Bangla social media, cyber security, cyberbullying detection, deep learning, multi-class classification, sexual harassment detection, spam detection