DeBot: Identifying Correlated Bots in Twitter

11:30 am - 11:50 am

Objective: Guidance
Audience Level: Advanced
Session Type: Presentation

We develop a technique to identify abnormally correlated user accounts in Twitter, which are very unlikely to be human. This new approach of bot detection considers cross-correlating user activities and requires no labeled data, as opposed to existing bot detection methods that consider users independently and require a large amount of labeled data.Our method, named DeBot, is 94% accurate and finds unique bots which reports them online every day .


, Research Assistant, University of New Mexico