Topical affinity in short text microblogs

Abstract

Knowledge-based applications like recommender systems in social networks are powered by complex network of social discussions and user connections. Short text microblog platforms like Twitter are powerful in this aspect due to their real-time content dissemination as well as having a complex mesh of user connections. For example, users on Twitter tend to consume certain content to a greater or less extent depending on their interests over time. Quantifying this degree of content consumption in certain topics is an arduous task. This is further compounded by the amount of digital information that such platforms generate at any given time. Formulation of personalized user profiles based on user interests over time and friendship network is thus a problem. Therefore, user profiling based on their interests is important for personalized third-party content recommendations on the platform. In this paper we address this problem by presenting our solution in a two-step process:- (i) Firstly, we compute users’ Degree of Interest (DoI) towards a certain topic based on the overall users’ affinity towards that topic. (ii) Secondly, we affirm this DoI by correlating it to their friendship network. Furthermore, we describe our model for DoI computation and follow-back recommendation system by learning a low-dimensional vector representation of users and their disseminated content. This representation is used to train models for prediction of correct cluster classifications. In our experiments, we use a Twitter dataset to validate our approach by computing degrees of interest for certain test users in three diverse and generic topics. Experimental results show the effectiveness of our approach in the extraction of intra-user interests and better accuracy in follow-back recommendations with diversities in the topics.