Emotional Community Detection in Social Network

Abstract

SUMMARYCommunity detection is a pivotal task in data mining, and users' emotional behaviors have an important impact on today's society. So it is very significant for society management or marketing strategies to detect emotional communities in social networks. Based on the emotional homophily of users in social networks, it could confirm that users would like to gather together to form communities according to emotional similarity. This paper exploits multivariate emotional behaviors of users to measure users' emotional similarity, then takes advantage of users' emotional similarity as edge weight to remodel an emotional network and detect communities. The detailed process of detecting emotional communities is as follows: 1) an emotional network is constructed and emotional homophily in experimental dataset is verified; 2) both CNM and BGLL algorithms are employed to detect emotional communities in emotional network, and emotional characters of each community are analyzed; 3) in order to verify the superiority of emotional network for detecting emotional communities, 1 unweighted network and 3 other weighted and undirected networks are constructed as comparison. Comparison experiments indicate that the emotional network is more suitable for detecting emotional communities, the users' emotional behaviors are more similar and denser in identical communities of emotional network than the contrastive networks' communities.

Multilevel Emotion Transfer on YouTube: Disentangling the Effects of Emotional Contagion and Homophily on Video Audiences

“…Regarding emotional flocking, past work found that people who express similarly valenced emotions on specific political topics were more frequently connected in network clusters on Twitter (Himelboim, Cameron, Sweetser, Danelo, & West, 2016;Yuan, Murukannaiah, Zhang, & Singh, 2014). More generally, online microblogging websites were argued to host emotion communities, which consist of interconnected users who are characterized by similar patterns of emotion expressions (Bollen et al, 2011;Zhu, Wang, Wu, & Zhang, 2017). The question of how far such communities are based on homophily versus emotional contagion (e.g., elicited by highly connected users) often remains unaddressed.…”

A Temporal User Attribute-Based Algorithm to Detect Communities in Online Social Networks

“…Consequently, the study identified the influence of each user to detect influential communities for which they use a modularity-based community detection algorithm [41]. Zhu, et al [42] also supposed that user emotions can affect the formation of a community. They investigated this issue in three phases: (i) they created an emotional network, (ii) they applied the CNM and BGLL algorithms to detect communities in the emotional network, and (iii) they compared their results with those of four other networks to verify their method.…”

Community detection in networks by dynamical optimal transport formulation

“…The detected communities may reveal important structural properties of the underlying system. Community detection has been used in diverse areas including, discovering potential friends on social networks 7 , evaluating social networks 8 , personalized recommendation of item to user 9 , detecting potential terrorist activities on social platforms 10 , fraud detection in finance 11 , study epidemic spreading process 12 and so on.…”