Finding Influentials in Twitter: A Temporal Influence Ranking Model

TL;DR

This paper introduces a temporal influence ranking model for Twitter that incorporates user activity patterns into influence measurement, outperforming existing models in stability and accuracy.

Contribution

The paper presents a novel PageRank-based model that integrates temporal activity patterns via logistic regression, enhancing influence ranking accuracy.

Findings

TIR outperforms existing models in influence ranking accuracy.

TIR demonstrates greater stability in influence measurement.

Incorporating temporal activity improves influence prediction.

Abstract

With the growing popularity of online social media, identifying influential users in these social networks has become very popular. Existing works have studied user attributes, network structure and user interactions when measuring user influence. In contrast to these works, we focus on user behavioural characteristics. We investigate the temporal dynamics of user activity patterns and how these patterns affect user interactions. We assimilate such characteristics into a PageRank based temporal influence ranking model (TIR) to identify influential users. The transition probability in TIR is predicted by a logistic regression model and the random walk, biased according to users' temporal activity patterns. Experiments demonstrate that TIR has better performance and is more stable than the existing models in global influence ranking and friend recommendation.