Title
Modeling and inferring mobile phone users' negative emotion spreading in social networks.
Abstract
Individual emotion, as an important part of personal privacy on health information, is vital for physical and emotional well-being. Despite the physiological reasons, emotion contagion between peoples is pivotal to understand people’s emotional changes. However, most existing works at the individual level focus on small groups in the short term. Because negative emotions are natural to appear and can largely affect the dynamics of emotion spreading, therefore this paper aims to investigate the negative emotion spreading mechanism at the individual level of large user groups in the long term, and finally infer individuals’ ability of the negative emotion spreading by observing people’s behaviors on mobile social networking. Specifically, we first propose a novel metric for measuring individuals’ degree of negative emotion spreading. We then put forward a Graph-Coupled Hidden Markov Sentiment Model for modeling the propagation of infectious negative sentiment locally within a social network using data collected by mobile phones. In this model, we assume that one can infect others even if he/she is not infected, which is an extension of the traditional assumption in epidemic spreading. Because the proposed model involves parameters, to infer those parameters, Gibbs sampling method is employed. Experiments on both synthetic and real-world network datasets are carried out, and the efficacy of our proposed model is verified. The case study on real-world, as a potential application, demonstrates that the proposed model provides a useful insight for understanding the correlation between network structure and the emotion shift.
Year
DOI
Venue
2018
10.1016/j.future.2017.04.015
Future Generation Computer Systems
Keywords
Field
DocType
Emotion contamination,Dynamic social networks,Latent Dirichlet Allocation,Gibbs sampling
Latent Dirichlet allocation,Social network,Computer science,Correlation,Artificial intelligence,Emotional Changes,Mobile phone,Hidden Markov model,Machine learning,Gibbs sampling,Distributed computing,Network structure
Journal
Volume
ISSN
Citations 
78
0167-739X
4
PageRank 
References 
Authors
0.43
14
5
Name
Order
Citations
PageRank
Zhanwei Du1249.82
Yongjian Yang23914.05
Qing Cai351.46
Zhang Chijun473.86
Yuan Bai541.11