An Agent-Based Approach to Modeling Online Social Influence
conference paper
The aim of this study is to better understand social influence in online social media. Therefore, we propose a method in which we implement, validate and improve an individual behavior model. The behavior model is based on three fundamental behavioral principles of social influence from the literature: 1) liking, 2) social proof and 3) consistency. We have implemented the model using an agent-based modeling approach. The multi-agent model contains the social network structure, individual behavior parameters and the scenario that are obtained from empirical data. The model is validated by comparing the output of the multi-agent simulation with empirical data. We demonstrate the method by evaluating five versions of behavior models applied to the use case of Twitter behavior about a talent show on Dutch television.
Topics
TNO Identifier
486584
Source title
ASONAM'13 Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining
Pages
600-607