Independent researcher Tao Zhu, working with colleagues at Rice University and the University of New Mexico, analyzed censorship practices of Sina Weibo, operator of the Weibo site, which -- like Twitter -- allows users to post 140-character messages with usernames and hashtags.
An estimated 300 million people use Weibo, posting 100 million messages each day.
"Other people have explored censorship on Weibo, but this work is focused on the speed at which censorship happens," Rice computer science Professor Dan Wallach, co-author of the study, said.
The researchers determined operator Sina Weibo uses a combination of keyword-matching software and human censors to monitor and delete potentially controversial posts on Weibo.
By closely monitoring individuals who frequently post controversial messages, Sina Weibo is able to delete many objectionable posts in less than 5 minutes, the study found.
"We have [examined] enough of these posts to be able to run topical analysis algorithms that let us extract the main subjects that Weibo's censors seemed concerned with on any given day," Wallach said.
Weibo faces the challenge of keeping its users engaged -- and thereby looking at advertisements and making money for Sina Weibo -- while keeping the content it hosts compliant with local laws, a challenge all such sites around the world must contend with, Wallach said.
"Weibo gives us a window into the future for what Internet censorship of social media around the world may look like."