Generative Models for Item Adoptions Using Social Correlation

Abstract

Users face many choices on the web when it comes to choosing which product to buy, which video to watch, and so on. In making adoption decisions, users rely not only on their own preferences, but also on friends. We call the latter social correlation, which may be caused by the homophily and social influence effects. In this paper, we focus on modeling social correlation on users item adoptions. Given a user-user social graph and an item-user adoption graph, our research seeks to answer the following questions: Whether the items adopted by a user correlate with items adopted by her friends, and how to model item adoptions using social correlation. We propose a social correlation framework that considers a social correlation matrix representing the degrees of correlation from every user to the users friends, in addition to a set of latent factors representing topics of interests of individual users. Based on the framework, we develop two generative models, namely sequential and unified, and the corresponding parameter estimation approaches. From each model, we devise the social correlation only and hybrid methods for predicting missing adoption links. Experiments on LiveJournal and Epinions data sets show that our proposed models outperform the approach based on latent factors only (LDA).

A Survey on Information Diffusion in Online Social Networks: Models and Methods

“…Researchers forecast the trends of information diffusion based on the characteristics of information diffusion analysis [83,84]. Jiuxin et al [85] propose a method that combines user attributes with social relationships and micro-blog contents to predict information diffusion.…”

A Brief Literature Survey on: Online Product Purchasing on User Behavior

“…But in [1] it has utilize a Social Correlation Framework that incorporates the social correlation matrix C in the generation of user-item adoption links. Within this framework, paper propose two generative models: Sequential Generative Model and Unified Generative Model.…”

Inferring continuous dynamic social influence and personal preference for temporal behavior prediction

“…Chua et al proposed generative approaches to modeling item-adoption behaviors based on social correlation [6]. Ye et al studied the direct impact of social influence on people's behaviors and proposed the SIS behavior model [25].…”

“…It motivates the study on behavior modeling and prediction, which focuses on modeling how these behaviors happen and predicting what behaviors will happen, respectively. In the literature, the personal preference and social influence are widely recognized as two major contributing factors for individual behaviors, and utilized to model, explain and predict the massive complicated behavior data [6,25,5,29,24,19]. Existing work, however, usually ignored the dynamic nature of behavior data and the underlying factors.…”