Topic Modelling Games

This paper presents a new topic modelling framework inspired by game theoretic principles. It is formulated as a normal form game in which words are represented as players and topics as strategies that the players select. The strategies of each player are modelled with a probability distribution guided by a utility function that the players try to maximize. This function induces players to select strategies similar to those selected by similar players and to choice strategies not shared with those selected by dissimilar players. The proposed framework is compared with state-of-the-art models demonstrating good performances on standard benchmarks.