ECANP: A Topic Influence Evaluation Model for Hot Topics

Abstract

Social network is an important product of industrial society. In recent years, the research related to hot topics has focused on topic detection, topic trend prediction, and topic tracking. However, the important role of topic influence evaluation in hot topic research has not received enough attention, which leads the problem of inaccurate influence calculation. In order to solve the above problems, this paper proposes a novel model to evaluate the real-time relative influence of topics in social network. The proposed model can quantify the influence of topics, and some influential factors which determine topic hotness will be analyzed and identified. In this model, five impact indicators are defined, namely user engagement, topic coverage, topic activity, topic persistence, and topic novelty to consider the topic characteristics more finely. Moreover, the proposed model not only consider traditional simple factors of like, forward and comments, but also pay attention to the relative influence and time attenuation characteristics of the topics. Further, the experimental results show that our method could quickly aggregate the influence factors of hot topics and accurately provide the influence indicator of topics.