Influence diffusion detection using the influence style (INFUSE) model

• Main Authors: Tan, Luke Kien-Weng, Na, Jin-Cheon, Ding, Ying
• Other Authors: Wee Kim Wee School of Communication and Information
• Format: Article
• Language: English
• Published: 2016
• Subjects: Natural language processing; Text mining; Text processing
• Online Access: https://hdl.handle.net/10356/80336; http://hdl.handle.net/10220/40481
• Institution: Nanyang Technological University

Blogs are readily available sources of opinions and sentiments that in turn could influence the opinions of the blog readers. Previous studies had attempted to infer influence from blog features, but they ignored the possible influence styles that describe the different ways or manner in which influence is exerted. In this paper, we propose a novel approach of analyzing bloggers’ influence styles, and using the influence styles as features to improve the performance of influence diffusion detection between linked bloggers. The proposed influence style (INFUSE) model describes bloggers’ influence through their engagement style, persuasion style, and persona. Methods used include similarity analysis to detect the creating-sharing aspect of engagement style, subjectivity analysis to measure persuasion style, and sentiment analysis to identify persona style. We further extend the INFUSE model to detect influence diffusion between linked bloggers based on the bloggers’ influence styles. The INFUSE model performed well with an average F1-score of 76% when compared to the in-degree and sentiment-value baseline approaches. While previous studies had focused on the existence of influence between linked bloggers in detecting influence diffusion, our INFUSE model is shown to provide a fine-grained description of the manner in which influence is diffused based on the bloggers’ influence styles.