A framework to analyze the emotional reactions to mass violent events on Twitter and influential factors
作者：
Highlights：
• a framework to analyze the emotional reactions to mass violent events on Twitter.
• use of the basic emotions to reveal the multiple dimensions of negative sentiment.
• study of the influence of user and event properties on the emotional reaction.
• analysis of eight mass shooting events to generalize the findings.
• experimented with CNN, biLSTM and BERT to develop emotion classifiers, trained automatically labeled datasets.
摘要
•a framework to analyze the emotional reactions to mass violent events on Twitter.•use of the basic emotions to reveal the multiple dimensions of negative sentiment.•study of the influence of user and event properties on the emotional reaction.•analysis of eight mass shooting events to generalize the findings.•experimented with CNN, biLSTM and BERT to develop emotion classifiers, trained automatically labeled datasets.
论文关键词：Deep learning,Emotion analysis,Mass shooting,Twitter
论文评审过程：Received 3 March 2020, Revised 30 July 2020, Accepted 11 August 2020, Available online 4 September 2020, Version of Record 20 October 2020.
论文官网地址：https://doi.org/10.1016/j.ipm.2020.102372
