Social velocity based spatio-temporal anomalous daily activity discovery of social media users

摘要

Anomalous daily activities are the activities that do not fit into normal daily behavior of social media users. Discovering anomalous daily activities is important for protecting social media users from harmful content and providing correct information about populated accounts, products, or hashtags. However, discovering anomalous daily activities is challenging due to hardness of detection of bot applications, complexity of anomalous activities, and the big data nature of social media datasets. In this study, a novel method that discovers anomalous daily activities with respect to spatio-temporal information of social media datasets is proposed. For this purpose, an interest measure, named as social velocity, is proposed to discover anomalous daily activities that is based on spatial distance and temporal difference of successive posts. Two novel algorithms are proposed that use proposed method and interest measure and experimentally evaluated on a real Twitter dataset. The experimental results show that proposed algorithms are successful for discovering anomalous activities of social media users with respect to spatio-temporal information.