The Velocity of Censorship: High-Fidelity Detection of Microblog Post Deletions

TL;DR

This study quantifies the speed and scope of censorship on Chinese microblogging sites like Weibo, revealing rapid deletion times and topic-specific censorship patterns through large-scale data analysis.

Contribution

It provides high-fidelity measurements of censorship timing and mechanisms on Weibo, including the speed of deletions and topic-based censorship behaviors, using extensive data analysis.

Findings

Most deletions occur within the first hour of posting

Nearly 30% of deletions happen within 5-30 minutes

90% of deletions occur within 24 hours

Abstract

Weibo and other popular Chinese microblogging sites are well known for exercising internal censorship, to comply with Chinese government requirements. This research seeks to quantify the mechanisms of this censorship: how fast and how comprehensively posts are deleted.Our analysis considered 2.38 million posts gathered over roughly two months in 2012, with our attention focused on repeatedly visiting "sensitive" users. This gives us a view of censorship events within minutes of their occurrence, albeit at a cost of our data no longer representing a random sample of the general Weibo population. We also have a larger 470 million post sampling from Weibo's public timeline, taken over a longer time period, that is more representative of a random sample. We found that deletions happen most heavily in the first hour after a post has been submitted. Focusing on original posts, not reposts/retweets, we observed that nearly 30% of the total deletion events occur within 5- 30 minutes. Nearly 90% of the deletions happen within the first 24 hours. Leveraging our data, we also considered a variety of hypotheses about the mechanisms used by Weibo for censorship, such as the extent to which Weibo's censors use retrospective keyword-based censorship, and how repost/retweet popularity interacts with censorship. We also used natural language processing techniques to analyze which topics were more likely to be censored.