Citation

Fei D. Safety Sci. 2019; 118: 757-762.

Copyright

(Copyright © 2019, Elsevier Publishing)

DOI

10.1016/j.ssci.2019.06.004

PMID

unavailable

Abstract

Emotion is a state that combines people's feelings, thoughts, and behaviors and plays an important role in the communication between people. Emotional recognition is the automatic identification of a person's emotional state by acquiring a person's physiological or non-physiological signals to achieve a more friendly and natural human-computer interaction. Similarities between the spread of infectious diseases and behavioral phenomena have been observed in large social networks. Accordingly, a framework for the spread of social phenomena, such as happiness and obesity, has been reported. Whereas this framework shows striking resemblance to the SIS-style infectious disease model, it does not demonstrate factors that influence the diameter of social networks, or explain the low degrees of separation among participants of the Framingham Heart study. The diameter is the primary parameter for understand the emotion contagions in large social networks. Although classical models for discussing these phenomena are available, models for the spread of happiness require factors that are relevant to emotional transmissions, such as the non-contact factors described in the previous SIS-style model. The proposed in this paper Markov chain-style random walk model robustly indicated a diameter of only 3 degrees of separation in this social network, and may represent the spread of happiness in these social networks more accurately than the SIS-style model.

Language: en

Keywords

Machine learning; Random walk; SIS infectious disease model; Social network diameter; Social networks security