# Nipping in the Bud: Detection, Diffusion and Mitigation of Hate Speech on Social Media

arXiv: https://arxiv.org/abs/2201.00961 · HTML: https://mlsanity.com/paper/2201.00961/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 4 Jan 2022.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets](https://mlsanity.com/paper/2109.05184/) (2021)
- [Detecting Harmful Memes and Their Targets](https://mlsanity.com/paper/2110.00413/) (2021)
- [Spread of hate speech in online social media](https://mlsanity.com/paper/1812.01693/) (2018)
- [All You Need is "Love": Evading Hate-speech Detection](https://mlsanity.com/paper/1808.09115/) (2018)
- [Aggression-annotated Corpus of Hindi-English Code-mixed Data](https://mlsanity.com/paper/1803.09402/) (2018)
- [Hate Speech in Pixels: Detection of Offensive Memes towards Automatic Moderation](https://mlsanity.com/paper/1910.02334/) (2019)
- [Multilingual Offensive Language Identification for Low-resource Languages](https://mlsanity.com/paper/2105.05996/) (2021)
- [KGTK: A Toolkit for Large Knowledge Graph Manipulation and Analysis](https://mlsanity.com/paper/2006.00088/) (2020)
- [Hate is the New Infodemic: A Topic-aware Modeling of Hate Speech Diffusion on Twitter](https://mlsanity.com/paper/2010.04377/) (2020)
- [A Corpus of English-Hindi Code-Mixed Tweets for Sarcasm Detection](https://mlsanity.com/paper/1805.11869/) (2018)
- [Countering Online Hate Speech: An NLP Perspective](https://mlsanity.com/paper/2109.02941/) (2021)
- [Humor Detection in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System](https://mlsanity.com/paper/1806.05513/) (2018)
- [Deep Exogenous and Endogenous Influence Combination for Social Chatter Intensity Prediction](https://mlsanity.com/paper/2006.07812/) (2020)
- [An English-Hindi Code-Mixed Corpus: Stance Annotation and Baseline System](https://mlsanity.com/paper/1805.11868/) (2018)
- [DiVA: A Scalable, Interactive and Customizable Visual Analytics Platform for Information Diffusion on Large Networks](https://mlsanity.com/paper/2112.06267/) (2021)

## Built on by (most cited first, 2 of 2)

- [Handling Bias in Toxic Speech Detection: A Survey](https://mlsanity.com/paper/2202.00126/) (2022)
- [Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities](https://mlsanity.com/paper/2406.07353/) (2024)

## Abstract (arXiv)

Since the proliferation of social media usage, hate speech has become a major crisis. Hateful content can spread quickly and create an environment of distress and hostility. Further, what can be considered hateful is contextual and varies with time. While online hate speech reduces the ability of already marginalised groups to participate in discussion freely, offline hate speech leads to hate crimes and violence against individuals and communities. The multifaceted nature of hate speech and its real-world impact have already piqued the interest of the data mining and machine learning communities. Despite our best efforts, hate speech remains an evasive issue for researchers and practitioners alike. This article presents methodological challenges that hinder building automated hate mitigation systems. These challenges inspired our work in the broader area of combating hateful content on the web. We discuss a series of our proposed solutions to limit the spread of hate speech on social media.