Automatic cyberbullying detection: A systematic review
作者：
Highlights：
• Cyberbullying is often misrepresented in automatic detection state-of-the-art.
• Available systems do not capture all four key criteria of cyberbullying.
• Datasets used to train detection systems are incomplete.
• Feature engineering performance improvement is marginal.
• Cyberbullying detection systems seem not applicable to real world situations.
摘要
•Cyberbullying is often misrepresented in automatic detection state-of-the-art.•Available systems do not capture all four key criteria of cyberbullying.•Datasets used to train detection systems are incomplete.•Feature engineering performance improvement is marginal.•Cyberbullying detection systems seem not applicable to real world situations.
论文关键词：Cyberbullying,Automatic cyberbullying detection,Natural language processing,Machine learning,Abusive language,Social networks
论文评审过程：Received 2 October 2018, Revised 5 December 2018, Accepted 11 December 2018, Available online 12 December 2018, Version of Record 29 December 2018.
论文官网地址：https://doi.org/10.1016/j.chb.2018.12.021
