mlsanityData to 13 Oct 2026

Deep Learning for User Comment Moderation

arXiv 1705.09993 ↗First posted 28 May 2017cs.CL cs.LGcited by 18

Not on the map. Why?

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.

Key facts. Cited by 18 papers in the map (data through 13 Oct 2026). First posted on arXiv 28 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 6; 2023: 1; 2024: 2; 2025: 3.

18 papers.

Sort:

  1. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  2. 2022Emotion Based Hate Speech Detection using Multimodal Learningcited by 18
  3. 2021HateBR: A Large Expert Annotated Corpus of Brazilian Instagram Comments for Offensive Language and Hate Speech Detectioncited by 15
  4. 2022Model Positionality and Computational Reflexivity: Promoting Reflexivity in Data Sciencecited by 13
  5. 2021Towards Equal Gender Representation in the Annotations of Toxic Language Detectioncited by 9
  6. 2021An Information Retrieval Approach to Building Datasets for Hate Speech Detectioncited by 9
  7. 2022Efficient, Uncertainty-based Moderation of Neural Networks Text Classifierscited by 7
  8. 2023Revisiting Hate Speech Benchmarks: From Data Curation to System Deploymentcited by 7
  9. 2021Toxicity Detection can be Sensitive to the Conversational Contextcited by 6
  10. 2022Overview of Abusive and Threatening Language Detection in Urdu at FIRE 2021cited by 5
  11. 2021IIITG-ADBU@HASOC-Dravidian-CodeMix-FIRE2020: Offensive Content Detection in Code-Mixed Dravidian Textcited by 2
  12. 2021MIPT-NSU-UTMN at SemEval-2021 Task 5: Ensembling Learning with Pre-trained Language Models for Toxic Spans Detectioncited by 1
6 more
  1. 2024A Systematic Survey of Natural Language Processing for the Greek Languagecited by 1
  2. 2022Effect of Toxic Review Content on Overall Product Sentimentcited by 0
  3. 2024A Unified Multi-Task Learning Architecture for Hate Detection Leveraging User-Based Informationcited by 0
  4. 2025Improving Multilingual Social Media Insights: Aspect-based Comment Analysiscited by 0
  5. 2025Web(er) of Hate: A Survey on How Hate Speech Is Typedcited by 0
  6. 2025FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalizationcited by 0