Rheault, Ludovic, and Andreea Musulan. "Efficient detection of online communities and social bot activity during electoral campaigns." Journal of Information Technology & Politics 18.3 (2021): 324-337.

This research addresses the pressing issue of social media manipulation during election campaigns, focusing on the detection and analysis of social bots. By employing a novel methodology that combines uniform manifold approximation and projection with user-level document embeddings, the study efficiently maps the community structure of social media users. This approach not only allows for the accurate prediction of users' partisan affiliations but also facilitates the identification of social bots and their geographic origins. Applied to the Twitter data from the 2019 Canadian electoral campaign, the findings reveal the strategic use of social bots by national actors and the presence of foreign bot clusters spreading far-right and environmental content. This methodology offers a powerful tool for uncovering and understanding the role of social bots in electoral processes.