Data Mining Approach for Anomaly Detection in Social Network Analysis

Nowadays, users are more addicted to the Online Social Networks (OSN's), a network in which many users, group of people, or a particular organization are Connected via network. Use of online Social Networks has exploded and thus, causing a need of studying and understanding user behavior. Several approaches have studied the identification of anomaly detection In this paper, We propose an efficient method for anomaly detection from social networks. The present study aims at detecting the abnormal activities exhibiting different behaviors in social media application using Behavior-based anomaly detection approach. Anomalous users are detected based on their behavioral dissimilarity from others. A rich feature set is proposed for outlier detection. A method for providing visual explanation for the results is also proposed. This analysis is carried out using Facebook dataset.