# Hate Speech and Offensive Content Detection in Indo-Aryan Languages: A Battle of LSTM and Transformers

arXiv: https://arxiv.org/abs/2312.05671 · HTML: https://mlsanity.com/paper/2312.05671/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 49 references that are in the map.
- First posted on arXiv 9 Dec 2023.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [Deep Learning for Hate Speech Detection in Tweets](https://mlsanity.com/paper/1706.00188/) (2017)
- [MuRIL: Multilingual Representations for Indian Languages](https://mlsanity.com/paper/2103.10730/) (2021)
- [Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages](https://mlsanity.com/paper/2212.05409/) (2022)
- [A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media](https://mlsanity.com/paper/1910.12574/) (2019)
- [Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation](https://mlsanity.com/paper/2009.09359/) (2020)
- [Deep Learning Models for Multilingual Hate Speech Detection](https://mlsanity.com/paper/2004.06465/) (2020)
- [Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis](https://mlsanity.com/paper/2010.04543/) (2020)
- [emoji2vec: Learning Emoji Representations from their Description](https://mlsanity.com/paper/1609.08359/) (2016)
- [BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification](https://mlsanity.com/paper/2208.07864/) (2022)
- [HABERTOR: An Efficient and Effective Deep Hatespeech Detector](https://mlsanity.com/paper/2010.08865/) (2020)
- [Does Transliteration Help Multilingual Language Modeling?](https://mlsanity.com/paper/2201.12501/) (2022)
- [Mind Your Language: Abuse and Offense Detection for Code-Switched Languages](https://mlsanity.com/paper/1809.08652/) (2018)
- [WLV-RIT at HASOC-Dravidian-CodeMix-FIRE2020: Offensive Language Identification in Code-switched YouTube Comments](https://mlsanity.com/paper/2011.00559/) (2020)
- [One to rule them all: Towards Joint Indic Language Hate Speech Detection](https://mlsanity.com/paper/2109.13711/) (2021)
- [Hostility Detection in Hindi leveraging Pre-Trained Language Models](https://mlsanity.com/paper/2101.05494/) (2021)
- [Overview of the HASOC Subtrack at FIRE 2022: Offensive Language Identification in Marathi](https://mlsanity.com/paper/2211.10163/) (2022)

## Built on by (most cited first, 4 of 4)

- [UNITYAI-GUARD: Pioneering Toxicity Detection Across Low-Resource Indian Languages](https://mlsanity.com/paper/2503.23088/) (2025)
- [A Survey on Automatic Online Hate Speech Detection in Low-Resource Languages](https://mlsanity.com/paper/2411.19017/) (2024)
- [BhashaSutra: A Task-Centric Unified Survey of Indian NLP Datasets, Corpora, and Resources](https://mlsanity.com/paper/2604.18423/) (2026)
- [NJUST-KMG at TRAC-2024 Tasks 1 and 2: Offline Harm Potential Identification](https://mlsanity.com/paper/2403.19713/) (2024)

## Abstract (arXiv)

Social media platforms serve as accessible outlets for individuals to express their thoughts and experiences, resulting in an influx of user-generated data spanning all age groups. While these platforms enable free expression, they also present significant challenges, including the proliferation of hate speech and offensive content. Such objectionable language disrupts objective discourse and can lead to radicalization of debates, ultimately threatening democratic values. Consequently, organizations have taken steps to monitor and curb abusive behavior, necessitating automated methods for identifying suspicious posts. This paper contributes to Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages (HASOC) 2023 shared tasks track. We, team Z-AGI Labs, conduct a comprehensive comparative analysis of hate speech classification across five distinct languages: Bengali, Assamese, Bodo, Sinhala, and Gujarati. Our study encompasses a wide range of pre-trained models, including Bert variants, XLM-R, and LSTM models, to assess their performance in identifying hate speech across these languages. Results reveal intriguing variations in model performance. Notably, Bert Base Multilingual Cased emerges as a strong performer across languages, achieving an F1 score of 0.67027 for Bengali and 0.70525 for Assamese. At the same time, it significantly outperforms other models with an impressive F1 score of 0.83009 for Bodo. In Sinhala, XLM-R stands out with an F1 score of 0.83493, whereas for Gujarati, a custom LSTM-based model outshined with an F1 score of 0.76601. This study offers valuable insights into the suitability of various pre-trained models for hate speech detection in multilingual settings. By considering the nuances of each, our research contributes to an informed model selection for building robust hate speech detection systems.