# Improved Abusive Comment Moderation with User Embeddings

arXiv: https://arxiv.org/abs/1708.03699 · HTML: https://mlsanity.com/paper/1708.03699/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2017.

## Built on by (most cited first, 9 of 9)

- [Large-Scale Hate Speech Detection with Cross-Domain Transfer](https://mlsanity.com/paper/2203.01111/) (2022)
- [Countering Online Hate Speech: An NLP Perspective](https://mlsanity.com/paper/2109.02941/) (2021)
- [CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network](https://mlsanity.com/paper/2303.03387/) (2023)
- [NLRG at SemEval-2021 Task 5: Toxic Spans Detection Leveraging BERT-based Token Classification and Span Prediction Techniques](https://mlsanity.com/paper/2102.12254/) (2021)
- [Toxicity Detection can be Sensitive to the Conversational Context](https://mlsanity.com/paper/2111.10223/) (2021)
- [Modeling Users and Online Communities for Abuse Detection: A Position on Ethics and Explainability](https://mlsanity.com/paper/2103.17191/) (2021)
- [Putting Context in Context: the Impact of Discussion Structure on Text Classification](https://mlsanity.com/paper/2402.02975/) (2024)
- [Not All Comments are Equal: Insights into Comment Moderation from a Topic-Aware Model](https://mlsanity.com/paper/2109.10033/) (2021)
- [A Systematic Survey of Natural Language Processing for the Greek Language](https://mlsanity.com/paper/2407.09861/) (2024)

## Abstract (arXiv)

Experimenting with a dataset of approximately 1.6M user comments from a Greek news sports portal, we explore how a state of the art RNN-based moderation method can be improved by adding user embeddings, user type embeddings, user biases, or user type biases. We observe improvements in all cases, with user embeddings leading to the biggest performance gains.