Quantifying the Effect of Sentiment on Topic Evolution in Chinese Microblog

Peng Fu, Zheng Lin, Hailun Lin, Fengcheng Yuan, Weiping Wang, Dan Meng

Abstract: The role of sentiment on topic evolution in social media is an interesting problem and has not been fully investigated. Quantifying the effect of sentiment on topic evolution can help people understand the relationship between sentiment and information diffusion. In this paper, we propose a method to identify the stages of topic evolution and introduce a new metric called popularity strength to measure their popularity. We also classify topics into four categories and quantify the effect of sentiment on different classes. Our findings show that “Good news illumines widely, and bad news flies quickly”, and sentiment has complex dynamics towards topic evolution.