Deception detection in Twitter

Abstract

Online Social Networks (OSNs) play a significant role in the daily life of hundreds of millions of people. However, many user profiles in OSNs contain deceptive information. Existing studies have shown that lying in OSNs is quite widespread, often for protecting a user’s privacy. In this paper, we propose a novel approach for detecting deceptive profiles in OSNs. We specifically define a set of analysis methods for detecting deceptive information about user genders and locations in Twitter. First, we collected a large dataset of Twitter profiles and tweets. Next, we defined methods for gender guessing from Twitter profile colors and names. Subsequently, we apply Bayesian classification and K-means clustering algorithms to Twitter profile characteristics (e.g., profile layout colors, first names, user names, and spatiotemporal information) and geolocations to analyze the user behavior. We establish the overall accuracy of each indicator through extensive experimentation with our crawled dataset. Based on the outcomes of our approach, we are able to detect deceptive profiles about gender and location with a reasonable accuracy.