Trust-Distrust-Aware Point-of-Interest Recommendation in Location-Based Social Network

Point-of-Interest (POI) recommendation is an important personalized service in location-based social network (LBSN) which has wide applications. Traditional Collaborative Filtering methods suffer from cold-start and data sparsity problem. They also ignore connections among users and lose the opportunity to provide more accurate and personalized recommendations. In this paper, we propose a hybrid approach which incorporates user preference, geographic influence and social trust into POI recommendation system. In contrast to other trust-aware recommendation works, our approach exploits distrust links and investigates their propagation effects. We use a modified normalized Jaccard coefficient to measure the trust and distrust score. Several series of experiments are conducted and the results show that our approach perform better than the traditional Collaborative Filtering in terms of accuracy and user satisfaction.

[1]  Xing Xie,et al.  GeoMF: joint geographical modeling and matrix factorization for point-of-interest recommendation , 2014, KDD.

[2]  Yingshu Li,et al.  Using crowdsourced data in location-based social networks to explore influence maximization , 2016, IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications.

[3]  Wei-Po Lee,et al.  Enhancing collaborative recommendation performance by combining user preference and trust-distrust propagation in social networks , 2016, Knowl. Based Syst..

[4]  Daniel Thalmann,et al.  Merging trust in collaborative filtering to alleviate data sparsity and cold start , 2014, Knowl. Based Syst..

[5]  Michael R. Lyu,et al.  A Survey of Point-of-interest Recommendation in Location-based Social Networks , 2016, ArXiv.

[6]  Weili Wu,et al.  Target coverage maximisation for directional sensor networks , 2017, Int. J. Sens. Networks.

[7]  Mehrnoush Shamsfard,et al.  Matrix Factorization with Explicit Trust and Distrust Side Information for Improved Social Recommendation , 2014, TOIS.

[8]  Lei Li,et al.  Cognitive Approach for Location Privacy Protection , 2018, IEEE Access.

[9]  Yingshu Li,et al.  Maximising influence in sensed heterogeneous social network with privacy preservation , 2018, Int. J. Sens. Networks.

[10]  Baoyu Zheng,et al.  Physical-Layer Security and Reliability Challenges for Industrial Wireless Sensor Networks , 2017, IEEE Access.

[11]  Chao Xu,et al.  A Collaborative Filtering Recommendation System by Unifying User Similarity and Item Similarity , 2011, WAIM Workshops.

[12]  Huan Liu,et al.  Content-Aware Point of Interest Recommendation on Location-Based Social Networks , 2015, AAAI.

[13]  Jinghua Zhu,et al.  A New Structure-Hole-Based Algorithm For Influence Maximization in Large Online Social Networks , 2017, IEEE Access.

[14]  Zhipeng Cai,et al.  Modeling Propagation Dynamics and Developing Optimized Countermeasures for Rumor Spreading in Online Social Networks , 2015, 2015 IEEE 35th International Conference on Distributed Computing Systems.

[15]  Guisheng Yin,et al.  A trust-based probabilistic recommendation model for social networks , 2015, J. Netw. Comput. Appl..

[16]  Yingshu Li,et al.  Truthful Incentive Mechanisms for Geographical Position Conflicting Mobile Crowdsensing Systems , 2018, IEEE Transactions on Computational Social Systems.

[17]  Guibing Guo,et al.  Integrating trust and similarity to ameliorate the data sparsity and cold start for recommender systems , 2013, RecSys.

[18]  Mao Ye,et al.  Exploiting geographical influence for collaborative point-of-interest recommendation , 2011, SIGIR.