International Symposium on Telecommunication (IST)

Home / 11th International Symposium on Telecommunication (IST'2024)

Measuring the social influence for retweet behavior prediction in microblogging network

Authors :

Rahebeh Mojtahedi safari¹ Amir Masoud Rahmani² Sasan H.Alizaeh³

1- Rahebeh Mojtahedi Safari Department of Computer and Information Technology Engineering, Lahijan Branch Islamic Azad University Lahijan, Iran 2- Future Technology Research Center, National Yunlin University of Science and Technology 123 University Road, Section 3, Douliou Yunlin 64002, Taiwan 3- Faculty of Information Technology ICT Research Institute (Iran Telecommunication Research Center) Tehran, Iran

Keywords :

Retweet behavior،influential factors،Retweet behavior prediction،Information diffusion

Abstract :

Nowadays, retweeting behavior is considered a substantial behavior to analyze information diffusion in the microblogging network. To understand the underlying mechanism of information diffusion and analyze the evolution of the diffusion corresponding to a given original microblog, user retweeting behavior prediction has recently gained considerable attention. In this paper firstly, we introduce the most influential factors which affect user retweeting behavior and propose an effective measurement based on the random walk model to measure the social influence. Secondly, by incorporating our defined influential factors into a logistic regression classifier model, we predict the future activated user set concerning the diffusion of a given original microblog at the next time point. Unlike other comparative models, our prediction model can illustrate the evolution of diffusion and predict the retweeting behavior of all potential users through the diffusion of any original microblog in the microblogging network. Finally, based on the real Twitter microblogging dataset, the experimental results show by the contribution of our defined influential factors and presenting an effective measure of the social influence factor, we can obtain more accurate predictions in comparison to other baseline methods.