acm-header
Sign In

Communications of the ACM

ACM TechNews

How Do You Spot a Russian Bot? Answer Goes Beyond Kremlin Watching


View as: Print Mobile App Share:
Examining code.

New York University researchers isolated the characteristics of bots on Twitter through an examination of bot activity related to Russian political discussions.

Credit: AndyEmel/iStock

Researchers at New York University (NYU) have isolated the characteristics of bots on Twitter by studying bot activity related to Russian political discussions.

Their research identifies how Russian accounts influence online exchanges using bots and trolls, with the goal of provoking unrest and disrupting civil discourse.

The findings reveal notable differences between human and bot-created posts, in addition to several similarities that could help hide bots from detection. For example, the researchers found that bots are much more likely to use online platforms while humans more often use mobile devices.

They focused on two specific time periods, both of which were notably consequential in Russian politics. The researchers analyzed about 15 million tweets sent from about 230,000 Russian Twitter accounts, including 93,000 that were active during both time periods. The researchers found that of those accounts active in both periods, about 67% of them were bots.

From New York University
View Full Article

 

Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA


 

No entries found