Evolution of passive user interests by analyzing Social Network activities

This paper addresses the issue of interest evolution based on social activities. The evolution of social interests emphasizes the use of various types of information and relationships between users. It’s based on social interactions (share, comment, like, etc.) and on resources (text, images, videos, etc.). Although evolution techniques have undergone distinct developments in recent years, they still have limitations, particularly when the user is inactive and the data is sparse. The evolution and detection of the passive user interests are challenging because this kind of user does not or rarely interacts in social networks and has few or no friends. In this paper, we present a novel evolutionary approach to detect the passive user interests based on the research history and resources clicked, taking into account the temporal factors of the information. We applied resource indexing, we elicited the top interests by calculating the weight of each term in queries, and we used a similarity function to further enrich the interests of passive users. An evolution system based on this approach has been developed, and experiments have been conducted using the Facebook social network. The evaluation results demonstrated that the proposed approach returns positive results and solves the cold start problem.