The DARPA Twitter Bot Challenge

TL;DR

The paper discusses DARPA's 2015 Twitter Bot Challenge, focusing on identifying influence bots on specific topics, highlighting the methods of top teams and the importance of ground truth in detection accuracy.

Contribution

It introduces the DARPA Twitter Bot Challenge and details the approaches of the top teams for influence bot detection on targeted topics.

Findings

Top teams employed diverse detection methods.

Ground truth data was crucial for evaluating accuracy.

The challenge advanced influence bot identification techniques.

Abstract

A number of organizations ranging from terrorist groups such as ISIS to politicians and nation states reportedly conduct explicit campaigns to influence opinion on social media, posing a risk to democratic processes. There is thus a growing need to identify and eliminate "influence bots" - realistic, automated identities that illicitly shape discussion on sites like Twitter and Facebook - before they get too influential. Spurred by such events, DARPA held a 4-week competition in February/March 2015 in which multiple teams supported by the DARPA Social Media in Strategic Communications program competed to identify a set of previously identified "influence bots" serving as ground truth on a specific topic within Twitter. Past work regarding influence bots often has difficulty supporting claims about accuracy, since there is limited ground truth (though some exceptions do exist [3,7]). However, with the exception of [3], no past work has looked specifically at identifying influence bots on a specific topic. This paper describes the DARPA Challenge and describes the methods used by the three top-ranked teams.