DPBT: A System for Detecting Pacemakers in Burst Topics

Guozhong DONG
Wu YANG
Feida ZHU, Singapore Management University
Wei WANG

Abstract

Influential users usually have a large number of followers and play an important role in the diffusion of burst topic. In this paper, pacemakers are defined as the influential users that promote topic diffusion in the early stages of burst topic. Traditional influential users detection approaches have largely ignored pacemakers in burst topics. To solve this problem, we present DPBT, a system that can detect pacemakers in burst topics. In DPBT, we construct burst topic user graph for each burst topic and propose a pacemakers detection algorithm to detect pacemakers in Twitter. The demonstration shows that DPBT is effective to detect pacemakers in burst topics, such that the historical detection results can effectively help to detect and predict burst topicsin the early stages.