What Does the Chirping Tell Us? Summarizing People's Opinion on Ongoing Events Using Tweets

摘要

The growth and increasing spatial resolution of Twitter has made it a promising network for assessing people ' s opinion regarding ongoing events in firsthand. However, while the richness of information content in Twitter is a boon for opinion miners, the huge traffic largely composed of insignificant chatter is a bane for them. In this paper, we propose a set of algorithms for filtering out tweets relevant to any ongoing event, which can serve as a real-time summary about people ' s opinion regarding the event. Evaluation conducted on a real-world dataset shows that the proposed model could achieve impressive precision and recall in summarizing tweets regarding the target event.