Identifying Sock-Puppets on Wikipedia: A Semantic Clustering Approach

The idea that information manipulation, even ‘information warfare’ poses a rising, even existential, threat to democracies is one of the most important of our age. Civic societal coalitions have sprung up to fight it. Global summits have been convened. New government task-forces have been created, as have academic centres, regulatory groups, and a fledgling industry of private-sector start-ups. Perhaps not since 9/11 have we seen such a fast and decisive pivot of so many different actors towards a single threat.

Malign activity has targeted a number of information environments, including every major social media platform: Twitter, Facebook, YouTube, Instagram, TikTok, standalone websites and many others. This paper, however, is dedicated to possible platform manipulation on a venue that tends to be much less researched than mainstream social media: Wikipedia.

This report presents work that set out to create, trial and evaluate a method to try to detect covert and organised manipulation of Wikipedia at scale. It aims to explore whether this method worked, and whether it might be useful if deployed more expansively.