# Deep Learning for User Comment Moderation

arXiv: https://arxiv.org/abs/1705.09993 · HTML: https://mlsanity.com/paper/1705.09993/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2017.

## Built on by (most cited first, 18 of 18)

- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Emotion Based Hate Speech Detection using Multimodal Learning](https://mlsanity.com/paper/2202.06218/) (2022)
- [HateBR: A Large Expert Annotated Corpus of Brazilian Instagram Comments for Offensive Language and Hate Speech Detection](https://mlsanity.com/paper/2103.14972/) (2021)
- [Model Positionality and Computational Reflexivity: Promoting Reflexivity in Data Science](https://mlsanity.com/paper/2203.07031/) (2022)
- [Towards Equal Gender Representation in the Annotations of Toxic Language Detection](https://mlsanity.com/paper/2106.02183/) (2021)
- [An Information Retrieval Approach to Building Datasets for Hate Speech Detection](https://mlsanity.com/paper/2106.09775/) (2021)
- [Efficient, Uncertainty-based Moderation of Neural Networks Text Classifiers](https://mlsanity.com/paper/2204.01334/) (2022)
- [Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment](https://mlsanity.com/paper/2306.01105/) (2023)
- [Toxicity Detection can be Sensitive to the Conversational Context](https://mlsanity.com/paper/2111.10223/) (2021)
- [Overview of Abusive and Threatening Language Detection in Urdu at FIRE 2021](https://mlsanity.com/paper/2207.06710/) (2022)
- [IIITG-ADBU@HASOC-Dravidian-CodeMix-FIRE2020: Offensive Content Detection in Code-Mixed Dravidian Text](https://mlsanity.com/paper/2107.14336/) (2021)
- [MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detection](https://mlsanity.com/paper/2104.04739/) (2021)
- [A Systematic Survey of Natural Language Processing for the Greek Language](https://mlsanity.com/paper/2407.09861/) (2024)
- [Effect of Toxic Review Content on Overall Product Sentiment](https://mlsanity.com/paper/2201.02857/) (2022)
- [A Unified Multi-Task Learning Architecture for Hate Detection Leveraging User-Based Information](https://mlsanity.com/paper/2411.06855/) (2024)
- [Improving Multilingual Social Media Insights: Aspect-based Comment Analysis](https://mlsanity.com/paper/2505.23037/) (2025)
- [Web(er) of Hate: A Survey on How Hate Speech Is Typed](https://mlsanity.com/paper/2506.16190/) (2025)
- [FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization](https://mlsanity.com/paper/2511.19248/) (2025)

## Abstract (arXiv)

Experimenting with a new dataset of 1.6M user comments from a Greek news portal and existing datasets of English Wikipedia comments, we show that an RNN outperforms the previous state of the art in moderation. A deep, classification-specific attention mechanism improves further the overall performance of the RNN. We also compare against a CNN and a word-list baseline, considering both fully automatic and semi-automatic moderation.