Paper Number
1953
Paper Type
Complete
Description
We propose an empirical setting to discover sentiment contagion in social media. We find that, after controlling for concurrent events, sentiment contagion exists in social media. We conduct additional analyses to explore how the source and valence of exposure contents and individual heterogeneity affect the degree of sentiment contagion. We find robust evidence of sentiment contagion not only in contents under the same thread but also under different threads of the same forum. Additional analysis provides evidence of negativity bias. In terms of individual heterogeneity, we find that more experienced social media users are less sensitive to sentiments in social media. Last, we find that social media users are more likely to become inactive in the long run after being exposed to more negative contents. Managerial and practical implications are discussed.
Recommended Citation
Lim, Hyungsoo; Wang, Jing; and Huang, Allen, "Social Media Sentiment Contagion" (2022). ICIS 2022 Proceedings. 9.
https://aisel.aisnet.org/icis2022/user_behaivor/user_behaivor/9
Social Media Sentiment Contagion
We propose an empirical setting to discover sentiment contagion in social media. We find that, after controlling for concurrent events, sentiment contagion exists in social media. We conduct additional analyses to explore how the source and valence of exposure contents and individual heterogeneity affect the degree of sentiment contagion. We find robust evidence of sentiment contagion not only in contents under the same thread but also under different threads of the same forum. Additional analysis provides evidence of negativity bias. In terms of individual heterogeneity, we find that more experienced social media users are less sensitive to sentiments in social media. Last, we find that social media users are more likely to become inactive in the long run after being exposed to more negative contents. Managerial and practical implications are discussed.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
19-UserBehavior