Fine-Grained Multilingual Hate Speech Detection Using Explainable AI and Transformers
Open Access
- 30 September 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 143177-143192
Abstract
The detection of hate speech on online platforms is essential for maintaining safe and inclusive digital environments. Although significant progress has been made in binary classification for hate speech detection, challenges persist in multilingual and fine-grained classification. This study presents a comprehensive model for hate speech detection across English, Urdu, and Sindhi, utilizing advanced deep learning models like Bidirectional Encoder Representations from Transformers (BERT) and its multilingual variants. Additionally, the research employs Explainable Artificial Intelligence (XAI) techniques, such as Local Interpretable Model-Agnostic Explanations (LIME), to gain insights into model performance. This work curated a multilingual hate speech detection dataset and a robust fine-grained hate speech detection model. The dataset includes non-hate and hate speech classes. Furthermore, the hate speech class is categorized into five fine-grained categories, including Disability, Gender, Nationality, Race, and Religion. Our experimental findings obtained 92% f-score in fine-grained hate speech detection for multilingual datasets using XLM-RoBERTa. It is believed that this study contributes to reducing the spread of hate speech (written in Either Urdu, English, or Sindhi) on various social media platforms.Keywords
This publication has 53 references indexed in Scilit:
- Multi-class hate speech detection in the Norwegian language using FAST-RNN and multilingual fine-tuned transformersComplex & Intelligent Systems, 2024
- Combining multiple pre-trained models for hate speech detection in Bengali, Marathi, and HindiMultimedia Tools and Applications, 2024
- HateDetector: Multilingual technique for the analysis and detection of online hate speech in social networksMultimedia Tools and Applications, 2023
- A survey on hate speech detection and sentiment analysis using machine learning and deep learning modelsAlexandria Engineering Journal, 2023
- Contents-Based Spam Detection on Social Networks Using RoBERTa Embedding and Stacked BLSTMSN Computer Science, 2023
- Hate speech recognition in multilingual text: hinglish documentsInternational Journal of Information Technology, 2023
- Multimodal Fake News Detection on Fakeddit Dataset Using Transformer-Based Architectures2022
- A Literature Review on Bidirectional Encoder Representations from Transformers2022
- A review on the long short-term memory modelArtificial Intelligence Review, 2020
- A Tutorial on the Cross-Entropy MethodAnnals of Operations Research, 2005