# Detecting harassment and defamation in cyberbullying with emotion-adaptive training

arXiv: https://arxiv.org/abs/2501.16925 · HTML: https://mlsanity.com/paper/2501.16925/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 82 references that are in the map.
- First posted on arXiv 28 Jan 2025.

## Builds on (most cited first, 21 of 21)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [How to Fine-Tune BERT for Text Classification?](https://mlsanity.com/paper/1905.05583/) (2019)
- [A Review on Language Models as Knowledge Bases](https://mlsanity.com/paper/2204.06031/) (2022)
- [Automatic Detection of Fake News](https://mlsanity.com/paper/1708.07104/) (2017)
- [EmoBank: Studying the Impact of Annotation Perspective and Representation Format on Dimensional Emotion Analysis](https://mlsanity.com/paper/2205.01996/) (2022)
- ["HOT" ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media](https://mlsanity.com/paper/2304.10619/) (2023)
- [Deep Learning for Detecting Cyberbullying Across Multiple Social Media Platforms](https://mlsanity.com/paper/1801.06482/) (2018)
- [GoodNewsEveryone: A Corpus of News Headlines Annotated with Emotions, Semantic Roles, and Reader Perception](https://mlsanity.com/paper/1912.03184/) (2019)
- [Emotion Detection for Misinformation: A Review](https://mlsanity.com/paper/2311.00671/) (2023)
- [DENS: A Dataset for Multi-class Emotion Analysis](https://mlsanity.com/paper/1910.11769/) (2019)
- [Session-based Cyberbullying Detection in Social Media: A Survey](https://mlsanity.com/paper/2207.10639/) (2022)
- [Cyberbullying detection across social media platforms via platform-aware adversarial encoding](https://mlsanity.com/paper/2204.00334/) (2022)
- [Online Harassment of Japanese Celebrities and Influencers](https://mlsanity.com/paper/2210.07599/) (2022)

## Built on by (most cited first, 1 of 1)

- [Cyberbullying Detection via Aggression-Enhanced Prompting](https://mlsanity.com/paper/2508.06360/) (2025)

## Abstract (arXiv)

Existing research on detecting cyberbullying incidents on social media has primarily concentrated on harassment and is typically approached as a binary classification task. However, cyberbullying encompasses various forms, such as denigration and harassment, which celebrities frequently face. Furthermore, suitable training data for these diverse forms of cyberbullying remains scarce. In this study, we first develop a celebrity cyberbullying dataset that encompasses two distinct types of incidents: harassment and defamation. We investigate various types of transformer-based models, namely masked (RoBERTa, Bert and DistilBert), replacing(Electra), autoregressive (XLnet), masked&permuted (Mpnet), text-text (T5) and large language models (Llama2 and Llama3) under low source settings. We find that they perform competitively on explicit harassment binary detection. However, their performance is substantially lower on harassment and denigration multi-classification tasks. Therefore, we propose an emotion-adaptive training framework (EAT) that helps transfer knowledge from the domain of emotion detection to the domain of cyberbullying detection to help detect indirect cyberbullying events. EAT consistently improves the average macro F1, precision and recall by 20% in cyberbullying detection tasks across nine transformer-based models under low-resource settings. Our claims are supported by intuitive theoretical insights and extensive experiments.