Evaluating Public Anxiety for Topic-Based Communities in Social Networks

Abstract

Although individual anxiety evaluation has been well studied, there is still not much work on evaluating public anxiety of groups, especially in the form of communities on social networks, which can be leveraged to detect mental healthness of a society. However, we cannot simply average individual anxiety scores to evaluate a community's public anxiety, because following factors should be considered: (1) impacts from interpersonal relations on each individual group member's anxiety levels (the <inline-formula><tex-math notation="LaTeX">${\tt Structural}$</tex-math></inline-formula> component); (2) topic-based discussions which reflect a community's anxiety status (the <inline-formula><tex-math notation="LaTeX">${\tt Topical}$</tex-math></inline-formula> component). In this paper, we initiate the study of evaluating public anxiety of Topic-based Social Network Communities ( <inline-formula><tex-math notation="LaTeX">$\textsc {TSNC}$</tex-math></inline-formula> ). We propose an evaluation framework to project the anxiety level of a <inline-formula><tex-math notation="LaTeX">$\textsc {TSNC}$</tex-math></inline-formula> into a score in the [0,1] range. We devise a cascading model to dynamically compute the individual anxiety scores using the <inline-formula><tex-math notation="LaTeX">${\tt Structural}$</tex-math></inline-formula> influence. We design a probabilistic model to measure anxiety score of social network messages using a generalized user, and compose a tree structure ( <inline-formula><tex-math notation="LaTeX">${\tt MC}$</tex-math></inline-formula> - <inline-formula><tex-math notation="LaTeX">${\tt Tree}$</tex-math></inline-formula> ) to effectively compute the anxiety score of a <inline-formula><tex-math notation="LaTeX">$\textsc {TSNC}$</tex-math></inline-formula> from the <inline-formula><tex-math notation="LaTeX">${\tt Topical}$</tex-math></inline-formula> aspect. For large communities, to avoid expensive real-time computing, we use a small sample to compute the public anxiety within given confidence interval. The effectiveness of our model are verified by precision and recall in an empirical study on real-world Weibo and Twitter data sets.