Visual Analytics using Topic Composition for Predicting Event Flow
토픽의 조합으로 이벤트 흐름을 예측하기 위한 시각적 분석 시스템

Hanbyul Yeon, Seokyeon Kim, Yun Jang
2015 KIISE Transactions on Computing Practices  
Emergence events are the cause of much economic damage. In order to minimize the damage that these events cause, it must be possible to predict what will happen in the future. Accordingly, many researchers have focused on real-time monitoring, detecting events, and investigating events. In addition, there have also been many studies on predictive analysis for forecasting of future trends. However, most studies provide future tendency per event without contextual compositive analysis. In this
more » ... nalysis. In this paper, we present a predictive visual analytics system using topic composition to provide future trends per event. We first extract abnormal topics from social media data to find interesting and unexpected events. We then search for similar emergence patterns in the past. Relevant topics in the past are provided by news media data. Finally, the user combines the relevant topics and a new context is created for contextual prediction. In a case study, we demonstrate our visual analytics system with two different cases and validate our system with possible predictive story lines.
doi:10.5626/ktcp.2015.21.12.768 fatcat:wootzt4mgbbz5b5e3n2t5ikdsi