WCSE 2019 SUMMER ISBN: 978-981-14-1684-2
DOI: 10.18178/wcse.2019.06.122

Enhancing Online Collaborative Filtering by Integrating Social Network

Shaobin Lu, Guilin Li

Abstract— In recent years, researchers have done a lot of work to enhance online collaborative filtering (OCF) performance. Compared to most of the offline collaborative filtering (offline CF), the online collaborative filtering algorithm has three advantages: the low cost of retraining the model, dynamically tracing the user behavior habits and capturing the change of the item popularity. Many OCF algorithms extract user interests and item popularity features by updating algorithms model in time. But most of OCF ignore the similarity of users or items by updating all users’ features or all items’ features. In this study, we aim to integrate social network to improve the OCF performance. In order to achieve the goal, we propose two new methods by introducing user similarity which obtains from user social network to online collaborative filtering based on the Probabilistic Matrix Factorization (PMF) frame. One of the methods, which we called OCFUSim_I, is to calculate the similarity of users and find the neighbors of user, then adding the neighbors to the OCF. Another method, called OCFUSim_II, is to add similarity among users to OCF model. We conduct the experiments on three public datasets: MovieLens100K, MovieLens1M and HetRec2011 datasets. The experimental results show that our algorithms achieve better performance than several baseline approaches.

Index Terms— Online Collaborative Filtering, Social Network, User Similarity, Recommend System

Shaobin Lu
Xiamen University, CHINA
Guilin Li
Research Center on Mobile Internet Technology, Software School of Xiamen University, CHINA

[Download]


Cite: Shaobin Lu, Guilin Li, "Enhancing Online Collaborative Filtering by Integrating Social Network," Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, pp. 820-828, Hong Kong, 15-17 June, 2019.