# Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language

arXiv: https://arxiv.org/abs/2110.09393 · HTML: https://mlsanity.com/paper/2110.09393/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 81 references that are in the map.
- First posted on arXiv 18 Oct 2021.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [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)
- [A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media](https://mlsanity.com/paper/1910.12574/) (2019)
- [The IIT Bombay English-Hindi Parallel Corpus](https://mlsanity.com/paper/1710.02855/) (2017)
- [Universal Language Model Fine-tuning for Text Classification](https://mlsanity.com/paper/1801.06146/) (2018)
- [One-step and Two-step Classification for Abusive Language Detection on Twitter](https://mlsanity.com/paper/1706.01206/) (2017)
- [Aggression-annotated Corpus of Hindi-English Code-mixed Data](https://mlsanity.com/paper/1803.09402/) (2018)
- [Hate Speech Detection: A Solved Problem? The Challenging Case of Long Tail on Twitter](https://mlsanity.com/paper/1803.03662/) (2018)
- [Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text](https://mlsanity.com/paper/1611.00472/) (2016)
- [Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations](https://mlsanity.com/paper/1910.00194/) (2019)
- [Hate Speech Detection from Code-mixed Hindi-English Tweets Using Deep Learning Models](https://mlsanity.com/paper/1811.05145/) (2018)
- [Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Text](https://mlsanity.com/paper/1906.05725/) (2019)
- [UM-IU@LING at SemEval-2019 Task 6: Identifying Offensive Tweets Using BERT and SVMs](https://mlsanity.com/paper/1904.03450/) (2019)
- [RiTUAL-UH at TRAC 2018 Shared Task: Aggression Identification](https://mlsanity.com/paper/1807.11712/) (2018)
- [Cross-lingual Word Sense Disambiguation using mBERT Embeddings with Syntactic Dependencies](https://mlsanity.com/paper/2012.05300/) (2020)

## Built on by (most cited first, 3 of 3)

- [Cyberbullying Detection for Low-resource Languages and Dialects: Review of the State of the Art](https://mlsanity.com/paper/2308.15745/) (2023)
- [User-Aware Multilingual Abusive Content Detection in Social Media](https://mlsanity.com/paper/2410.21321/) (2024)
- [Cyberbullying Detection in Hinglish Text Using MURIL and Explainable AI](https://mlsanity.com/paper/2506.16066/) (2025)

## Abstract (arXiv)

Social media has become a bedrock for people to voice their opinions worldwide. Due to the greater sense of freedom with the anonymity feature, it is possible to disregard social etiquette online and attack others without facing severe consequences, inevitably propagating hate speech. The current measures to sift the online content and offset the hatred spread do not go far enough. One factor contributing to this is the prevalence of regional languages in social media and the paucity of language flexible hate speech detectors. The proposed work focuses on analyzing hate speech in Hindi-English code-switched language. Our method explores transformation techniques to capture precise text representation. To contain the structure of data and yet use it with existing algorithms, we developed MoH or Map Only Hindi, which means "Love" in Hindi. MoH pipeline consists of language identification, Roman to Devanagari Hindi transliteration using a knowledge base of Roman Hindi words. Finally, it employs the fine-tuned Multilingual Bert and MuRIL language models. We conducted several quantitative experiment studies on three datasets and evaluated performance using Precision, Recall, and F1 metrics. The first experiment studies MoH mapped text's performance with classical machine learning models and shows an average increase of 13% in F1 scores. The second compares the proposed work's scores with those of the baseline models and offers a rise in performance by 6%. Finally, the third reaches the proposed MoH technique with various data simulations using the existing transliteration library. Here, MoH outperforms the rest by 15%. Our results demonstrate a significant improvement in the state-of-the-art scores on all three datasets.