Content based Social Behavior Prediction: A Multi-task Learning Approach

摘要

The study of information flow analyzes the principles and mechanisms of social information distribution. It is becoming an extremely important research topic in social network research. Traditional approaches are primarily based on the social network graph topology. However, topology itself can not accurately reflect user interests or behavior. In this paper, we adopt a "microeconomics" approach to study social information diffusion. In particular, we aim to answer the question that how social information flow and socialization behaviors are related to content similarities and user interests. We study content-based social activity prediction, i.e.. to predict a user's response (e.g. comment or like) to their friends' postings (e.g. blogs) w.r.t. message content. In our solution, we cast the social behavior prediction problem as a multi-task learning problem, in which each task corresponds to a user. We have designed a novel multi-task learning algorithm for predicting information flow in social networks. In our model, we apply ι_1 and Tikhonov regularization to obtain a sparse and smooth model in a linear multi-task learning framework. With comprehensive experiments, we have demonstrated the effectiveness of the proposed learning method.