Tweeting under pressure: analyzing trending topics and evolving word choice on sina weibo

In recent years, social media has risen to prominence in China, with sites like Sina Weibo and Renren each boasting hundreds of millions of users. Social media in China plays a profound role as a platform for breaking news and political commentary that is not available in the state-sanctioned news media. However, like all websites in China, Chinese social media is subject to censorship. Although several studies have identified censorship on Weibo and Chinese blogs, to date no studies have examined the overall impact of censorship on discourse in social media. In this study, we examine how censorship impacts discussions on Weibo, and how users adapt to avoid censorship. We gather tweets and comments from 280K politically active Weibo users for 44 days and use NLP techniques to identify trending topics. We observe that the magnitude of censorship varies dramatically across topics, with 82% of tweets in some topics being censored. However, we find that censorship of a topic correlates with high user engagement, suggesting that censorship does not stifle discussion of sensitive topics. Furthermore, we find that users adopt variants of words (known as morphs) to avoid keyword-based censorship. We analyze emergent morphs to learn how they are adopted and spread by the Weibo user community.