Assigning users to domains of interest based on content and network similarity with champion instances
Mattia Gasparini, Giorgia Ramponi, Marco Brambilla, Stefano Ceri · 2019
In this paper, we propose two approaches to the problem of finding similar users to a set of champions representing domains of interest on social media. The first approach is based on the content shared by the users, while the second one relies on the social network connections (following, followers, and mentions). Given a small set of champion accounts, we construct a centroid and we rank candidates by computing their distance from the centroid. Experiments show that social network features provide better performance, but they are computationally much more intensive. This approach can be used for providing highly reliable recommendations of the top-k instances which are most similar to a given target, specified through examples rather than through specific properties.