# DeepHateExplainer: Explainable Hate Speech Detection in Under-resourced Bengali Language

arXiv: https://arxiv.org/abs/2012.14353 · HTML: https://mlsanity.com/paper/2012.14353/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2020.

## Built on by (most cited first, 26 of 26)

- [Hate Speech and Offensive Language Detection in Bengali](https://mlsanity.com/paper/2210.03479/) (2022)
- [Multimodal Hate Speech Detection from Bengali Memes and Texts](https://mlsanity.com/paper/2204.10196/) (2022)
- [Endangered Languages are not Low-Resourced!](https://mlsanity.com/paper/2103.09567/) (2021)
- [BD-SHS: A Benchmark Dataset for Learning to Detect Online Bangla Hate Speech in Different Social Contexts](https://mlsanity.com/paper/2206.00372/) (2022)
- [Meme-ingful Analysis: Enhanced Understanding of Cyberbullying in Memes Through Multimodal Explanations](https://mlsanity.com/paper/2401.09899/) (2024)
- [Offensive Language Identification in Transliterated and Code-Mixed Bangla](https://mlsanity.com/paper/2311.15023/) (2023)
- [Explainable AI for Bioinformatics: Methods, Tools, and Applications](https://mlsanity.com/paper/2212.13261/) (2022)
- [Cyberbullying Detection for Low-resource Languages and Dialects: Review of the State of the Art](https://mlsanity.com/paper/2308.15745/) (2023)
- [Table Question Answering for Low-resourced Indic Languages](https://mlsanity.com/paper/2410.03576/) (2024)
- [HS-BAN: A Benchmark Dataset of Social Media Comments for Hate Speech Detection in Bangla](https://mlsanity.com/paper/2112.01902/) (2021)
- [A Biomedical Knowledge Graph for Biomarker Discovery in Cancer](https://mlsanity.com/paper/2302.04737/) (2023)
- [The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages](https://mlsanity.com/paper/2310.14557/) (2023)
- [Explain Thyself Bully: Sentiment Aided Cyberbullying Detection with Explanation](https://mlsanity.com/paper/2401.09023/) (2024)
- [BIDWESH: A Bangla Regional Based Hate Speech Detection Dataset](https://mlsanity.com/paper/2507.16183/) (2025)
- [Parameter-Efficient Fine-Tuning for Low-Resource Languages: A Comparative Study of LLMs for Bengali Hate Speech Detection](https://mlsanity.com/paper/2510.16985/) (2025)
- [Unveiling Black-boxes: Explainable Deep Learning Models for Patent Classification](https://mlsanity.com/paper/2310.20478/) (2023)
- [A Survey on Automatic Online Hate Speech Detection in Low-Resource Languages](https://mlsanity.com/paper/2411.19017/) (2024)
- [Milestones in Bengali Sentiment Analysis leveraging Transformer-models: Fundamentals, Challenges and Future Directions](https://mlsanity.com/paper/2401.07847/) (2024)
- [Probing the Information Encoded in Neural-based Acoustic Models of Automatic Speech Recognition Systems](https://mlsanity.com/paper/2402.19443/) (2024)
- [HarmPot: An Annotation Framework for Evaluating Offline Harm Potential of Social Media Text](https://mlsanity.com/paper/2403.11108/) (2024)
- [What Matters in Explanations: Towards Explainable Fake Review Detection Focusing on Transformers](https://mlsanity.com/paper/2407.21056/) (2024)
- [HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigation](https://mlsanity.com/paper/2507.04350/) (2025)
- [HCDIR: End-to-end Hate Context Detection, and Intensity Reduction model for online comments](https://mlsanity.com/paper/2312.13193/) (2023)
- [Demarked: A Strategy for Enhanced Abusive Speech Moderation through Counterspeech, Detoxification, and Message Management](https://mlsanity.com/paper/2406.19543/) (2024)
- [PromptGuard at BLP-2025 Task 1: A Few-Shot Classification Framework Using Majority Voting and Keyword Similarity for Bengali Hate Speech Detection](https://mlsanity.com/paper/2510.09771/) (2025)
- [BengaliSent140: A Large-Scale Bengali Binary Sentiment Dataset for Hate and Non-Hate Speech Classification](https://mlsanity.com/paper/2601.20129/) (2026)

## Abstract (arXiv)

The exponential growths of social media and micro-blogging sites not only provide platforms for empowering freedom of expressions and individual voices, but also enables people to express anti-social behaviour like online harassment, cyberbullying, and hate speech. Numerous works have been proposed to utilize textual data for social and anti-social behaviour analysis, by predicting the contexts mostly for highly-resourced languages like English. However, some languages are under-resourced, e.g., South Asian languages like Bengali, that lack computational resources for accurate natural language processing (NLP). In this paper, we propose an explainable approach for hate speech detection from the under-resourced Bengali language, which we called DeepHateExplainer. Bengali texts are first comprehensively preprocessed, before classifying them into political, personal, geopolitical, and religious hates using a neural ensemble method of transformer-based neural architectures (i.e., monolingual Bangla BERT-base, multilingual BERT-cased/uncased, and XLM-RoBERTa). Important(most and least) terms are then identified using sensitivity analysis and layer-wise relevance propagation(LRP), before providing human-interpretable explanations. Finally, we compute comprehensiveness and sufficiency scores to measure the quality of explanations w.r.t faithfulness. Evaluations against machine learning~(linear and tree-based models) and neural networks (i.e., CNN, Bi-LSTM, and Conv-LSTM with word embeddings) baselines yield F1-scores of 78%, 91%, 89%, and 84%, for political, personal, geopolitical, and religious hates, respectively, outperforming both ML and DNN baselines.