Social media is changing existing information behavior by giving users access to real-time online information channels without the constraints of time and space. Social media, therefore, has created an enormous data analysis challenge for scientists trying to keep pace with developments in their field. Most previous studies have adopted broad-brush approaches that typically result in limited analysis possibilities. To address this problem, we applied text-mining techniques to Twitter data related to the 2012 Korean presidential election. We use three primary techniques: topic modeling to track changes in topical trends, mention-direction-based user network analysis, and term co-occurrence retrieval for further content analysis. Our study reveals that Twitter could be a useful way to detect and trace the advent of and changes in social issues, while analyzing mention-based user networks could show different aspects of user behaviors.
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications
- Artificial Intelligence