When Social Influence Meets Item Inference

Abstract

Research issues and data mining techniques for product recommendation and viral marketing have been widely studied. Existing works on seed selection in social networks do not take into account the effect of product recommendations in e-commerce stores. In this paper, we investigate the seed selection problem for viral marketing that considers both effects of social influence and item inference (for product recommendation). We develop a new model, Social Item Graph (SIG), that captures both effects in form of hyperedges. Accordingly, we formulate a seed selection problem, called Social Item Maximization Problem (SIMP), and prove the hardness of SIMP. We design an efficient algorithm with performance guarantee, called Hyperedge-Aware Greedy (HAG), for SIMP and develop a new index structure, called SIG-index, to accelerate the computation of diffusion process in HAG. Moreover, to construct realistic SIG models for SIMP, we develop a statistical inference based framework to learn the weights of hyperedges from data. Finally, we perform a comprehensive evaluation on our proposals with various baselines. Experimental result validates our ideas and demonstrates the effectiveness and efficiency of the proposed model and algorithms over baselines.

Approximating special social influence maximization problems

“…The social influence maximization problem (called the profit-maximization SIMP), which is non-monotone, is discussed in Ref. [14]. For monotone non-submodular functions, we use the supermodular degree to evaluate its violation of submodularity.…”

“…For example, the minimum submodular cover problem with linear cost [13] , negative submodular functions [4] , and non-submodular problems, e.g., Refs. [6,[14][15][16], are all more complex. Hung et al [14] studied a variation of the SIMP with multiple items.…”

“…[6,[14][15][16], are all more complex. Hung et al [14] studied a variation of the SIMP with multiple items. Their problem is NP-hard and non-submodular, and thus, only heuristic algorithms are provided because the problem of nonsubmodular function maximization [6] has not been perfectly solved in Ref.…”

Joint Topic-Semantic-aware Social Recommendation for Online Voting

“…For example, [12] represents a social network as a star-structured hybrid graph centered on a social domain which connects with other item domains to help improve the prediction accuracy. [10] investigates the seed selection problem for viral marketing that considers both e ects of social in uence and item inference for product recommendation. [29] studies the e ects of strong and weak ties in social recommendation, and extends Bayesian Personalized Ranking model to incorporate the distinction of strong and weak ties.…”

“…ough several prior works [3,6,10,12,25,29,31,32] have been proposed to leverage social network information in recommendation, it is still an open question how to comprehensively incorporate structural social information into the task of voting recommendation considering its propagation pa ern. Second, users' interest in votings is strongly connected with voting content presented in question text (e.g., "Who is your favorite movie star?").…”