/Abuse-Detection

Repository for Studying Abuse Detection (Abusive Language Detection)

Abuse-Detection

Repository for Studying Abuse Detection (Abusive Language Detection)

To Read Paper List

Abuse Detection을 다룬 연구 논문 2개 이상의 연구자는 따로 분리해서 섹션을 만들었으며, 섹션 내에서 읽을 만한 순서를 고려하여 정리 (정확한 순서는 아님).
I make section dividing researchers published more than two papers about abuse detection.

  • Pushkar Mishra (University of Cambridge, Facebook AI London) [profile]

    • Author Profiling for Abuse Detection [paper]
      Pushkar Mishra, Macro Del Tredici, Helen Yannakoudakis, Ekaterina Shutova
      Proceedings of the 27th International Conference on Computational Linguistics (COLING) 2018

    • Neural Character-based Composition Models for Abuse Detection [paper]
      Pushkar Mishra, Helen Yannakoudakis, Ekaterina Shutova
      Proceedings of the Empirical Methods in Natural Language Processing (EMNLP) Workshop on Abusive Language Online 2018

    • Abusive Language Detection with Graph Convolution Networks [paper]
      Pushkar Mishra, Macro Del Tredici, Helen Yannakoudakis, Ekaternia Shutova
      Proceedings of the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)

    • Tackling Online Abuse: A Survey of Automated Abuse Detection Methods [paper]
      Pushkar Mishra, Helen Yannakoudakis, Ekaternia Shutova
      Preprint

  • Waseem and Hovy

    • To be updated

  • Ji Ho Park (HKUST, Oyalabs) [profile]

    • One-step and two-step classification for abusive language detection on twitter [paper]
      Ji Ho Park and Pascale Fung
      Proceedings of the First Workshop on Abusive Language Online, ACL 2017

    • Reducing Gender Bias in Abusive Language Detection [paper]
      Ji Ho Park, Jamin Shin, Pascale Fung
      Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

  • Other Researchers

    • Online abuse detection: the value of preprocessing and neural attention models [paper] [code]
      Dhruv Kumar, Robin Cohen, Lukasz Golab
      Proceedings of the Tenth Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA 2019) | NAACL-HLT workshop 2019

Dataset

  • Hate Speech [dataset]
    Twitter dataset of 16,914 tweets with racism, sexism, or neither.