An Information Sources Tracking Model Based on Instant Messaging Network

Abstract

Currently, information sources cannot be tracked effectively. Aiming at this problem, this paper proposes an information sources tracking model based on instant messaging network and Strogatz (WS) small-world network model with N nodes. The proposed model uses the concept of a ＂group＂ to describe ＂group communication＂ in the instant messaging network. The information propagation rule is established according to an improved Susceptible- Infected-Recovered (SIR) model. For one message in this improved SIR model, each node is characterized by four states: unknown state, receiving state, known state, and propagating state. Then, we simulated the simultaneous propagation of four messages in this model. After propagating the messages T times, the results are classified by Support Vector Machine (SVM) according to keywords. The first message is the information source of that category. Experimental results demonstrate that the proposed model can simulate the propagation process of an instant messaging network and track information sources effectively.