Skip to content. | Skip to navigation

Sections
Personal tools
You are here: Home Publications DeepHateExplainer: ExplainableHate Speech Detection in Under-resourced Bengali Language

Contact

Prof. Dr. S. Decker
RWTH Aachen
Informatik 5
Ahornstr. 55
D-52056 Aachen
Tel +49/241/8021501
Fax +49/241/8022321

How to find us

Annual Reports

Disclaimer

Webmaster

 

 

DeepHateExplainer: ExplainableHate Speech Detection in Under-resourced Bengali Language

Year 2021
Abstract URL view
PDF URL view

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 the 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. In our approach, 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). Subsequently, important (most and least) terms are 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.

Details

IEEE International Conference on Data Science and Advanced Analytics (DSAA'2021)

Presented at

IEEE International Conference on Data Science and Advanced Analytics, 2021 , PT.

Published in

DSAA'2021 .

Document Actions