International Conference on Weblogs and Social Media

Contact Information
For questions, please e-mail:


March 26-28, 2007

Understanding Sentiment of People from News Articles: Temporal Sentiment Analysis of Social Events

Tomohiro Fukuhara, Hiroshi Nakagawa and Toyoaki Nishida

Temporal sentiment analysis that analyzes temporal trends of sentiments and topics from a text archive that has timestamps is proposed. The method accepts texts with timestamp such as Weblog and news articles, and produces two kinds of graphs, i.e., (1) topic graph that shows temporal change of topics associated with a sentiment, and (2) sentiment graph that shows temporal change of sentiments associated with a topic. Sample results obtained by applying the method to news articles are described.


Available as PDF