Personality Trait Identification Based on Hidden semi-Markov Model in Online Social Networks

Abstract

In recent years, online social networks (OSNs) have become great places for people to communicate with each other and share knowledge. However, OSNs have also become the main grounds for exploiting the vulnerabilities of people and launching a variety of fraud. Most of hackers implement fraud based on the target users’ personality traits. It is difficult for users to identify such fraud in OSNs. In order to alert users to the hackers’ fraud strategies, and improve users’ ability to identify fraud, the research on personality trait identification is important. In this paper a new method is presented for identifying user's personality trait based on the personality trait dictionary and hidden semi-Markov models, from the perspective of the behavior process of user's posting/forwarding information in OSNs. The proposed method includes a training phase and an identification phase. In the identification phase, the average log likelihood of every observation sequence is calculated. An experiment based on real datasets of Weibo is conducted to evaluate this method. The experiment results validate the effectiveness of this method.