Direct and Indirect Influence on Likes in Social Media

2026-06-22

AI Summary

This study investigates the mechanisms through which users’ liking behavior on social media is influenced by direct and indirect social contagion. Leveraging large-scale data from approximately 290,000 users on the VKontakte platform, the analysis integrates local network structure and neighbor activity levels to assess the impact of first- and second-order neighborhoods on the probability of liking content. The findings reveal that even in the absence of directly active friends, active second-order neighbors significantly increase the likelihood of a user liking a post, whereas third-order and higher neighborhoods exhibit no significant effect. The work provides novel empirical support for the “structural diversity hypothesis,” demonstrating that the number of connected components formed by active friends serves as a key predictor and substantially improves behavioral prediction performance. Methodologically, the study combines large-scale graph feature extraction, social contagion modeling, and statistical association analysis.

Abstract

The present study investigates direct and indirect social contagion mechanisms in an online social network environment. Using a large-scale dataset comprising approximately 290,000 users from the VKontakte platform, we examine the factors associated with the probability that a user likes a post. Our analysis shows that, while demographic and structural characteristics of individual nodes, such as gender and degree, contribute to the observed dynamics, the strongest associations arise from activity in the user's local network. In particular, active nodes (users who have already liked the post) at distances d = 1 and d = 2 play a central role in shaping liking behavior. We find a substantial association between second-order activity and liking probability, which persists even in the absence of active direct neighbors and is consistent with indirect influence pathways in the network. No significant association is detected for nodes at distance three or beyond. The results also support the structural diversity hypothesis: the number of connected components among active friends is a significant predictor of liking.

Problem

• social contagion
• indirect influence
• online social network
• liking behavior
• structural diversity

Innovation

• social contagion
• indirect influence
• structural diversity
• network distance
• online social networks