Comparing Emotional Reactions to Terrorism Events on Twitter.
BiDU@VLDB(2018)
摘要
Over the last years, terrorism attempts have threatened the global population safety, impacting people in a complex emotional way. In this paper, we apply deep learning techniques to classify emotions of terrorism events, and develop a comparative analysis about emotional reactions on four events based on the demographics of tweeters, particularly gender, age and location. Our research questions involve comparing these events in terms of emotional shift, emotions according to age and gender, emotional reaction according to the closeness of the event and number/type of victims, as well as the terms used to express emotional reactions. The main conclusions were: fear, anger and sadness are the most expressed emotions; the emotions can be related to gender (e.g. fear for women, and anger for men); emotions seem to be not related to the closeness of the events, but seem to be affected by the casualties (number of kills/injuries); tweeters expressing fear and sadness tend to share words of affection and support, while tweeters expressing anger tend to use intense words of hate, intolerance and anger.
更多查看译文
关键词
Emotion analysis, Twitter, Deep learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络