User behavior mining on social media: a systematic literature review

Abstract

User behavior mining on Social Media (UBMSM) is the process of representing, analyzing, and extracting operational and behavioral patterns from user behavioral data in social media. It discusses theories and methodologies from different disciplines such as combining theorems and techniques from computer science, data mining, machine learning, social network analysis, and other related disciplines. User behavior mining provides a deep understanding of user behavioral data such that we observe not only individual behavioral patterns, but also interaction and communication among users by considering collective behavior of users. The aim of this study is to provide a systematic literature review on the significant aspects and approaches in addressing user behavior mining on social media. A systematic literature review was performed to find the related literature, and 174 articles were selected as primary studies. We classified the surveyed studies into four categories based on their focused area: users, user-generated content, the structure of network that content spreads on it and information diffusion. The majority of the primary articles focus on user aspect (66%); 6% of them focus on content aspect; 6% of them focus on network structure aspect, 22% of them focus on information diffusion aspect.