作者: Pasquale De Meo , Emilio Ferrara , Domenico Rosaci , Giuseppe M. L. Sarne
DOI: 10.1109/TCYB.2014.2323892
关键词:
摘要: Understanding the dynamics behind group formation and evolution in social networks is considered an instrumental milestone to better describe how individuals gather form communities, they enjoy share platform contents, are driven by their preferences/tastes, behaviors influenced peers. In this context, notion of compactness a particularly relevant. While literature usually refers as measure merely determine much members similar among each other, we argue that mutual trustworthiness between should be important factor defining such term. fact, trust has profound effects on evolution: more likely join with stay if can other members. paper, propose quantitative takes into account both similarity users, present algorithm optimize measure. We provide empirical results, obtained from real EPINIONS CIAO, compare our versus traditional user similarity, clearly proving advantages approach.