10th IEEE International Conference on Collaborative Computing: Networking, Applications and Worksharing

Research Article

Multi-Objective Optimization Based Location and Social Network Aware Recommendation

Download661 downloads
  • @INPROCEEDINGS{10.4108/icst.collaboratecom.2014.257382,
        author={Makbule Gulcin Ozsoy and Faruk Polat and Reda Alhajj},
        title={Multi-Objective Optimization Based Location and Social Network Aware Recommendation},
        proceedings={10th IEEE International Conference on Collaborative Computing: Networking, Applications and Worksharing},
        publisher={IEEE},
        proceedings_a={COLLABORATECOM},
        year={2014},
        month={11},
        keywords={recommendation systems location and social network aware multi objective filtering},
        doi={10.4108/icst.collaboratecom.2014.257382}
    }
    
  • Makbule Gulcin Ozsoy
    Faruk Polat
    Reda Alhajj
    Year: 2014
    Multi-Objective Optimization Based Location and Social Network Aware Recommendation
    COLLABORATECOM
    IEEE
    DOI: 10.4108/icst.collaboratecom.2014.257382
Makbule Gulcin Ozsoy1,*, Faruk Polat1, Reda Alhajj2
  • 1: Department of Computer Engineering, Middle East Technical University
  • 2: Department of Computer Science, University of Calgary
*Contact email: e1395383@ceng.metu.edu.tr

Abstract

Social networks, personal blog pages, on-line transaction web-sites, expertise web pages and location based social networks provide an attractive platform for millions of users to share opinions, comments, ratings, etc. Having this kind of diverse and comprehensive information leads to difficulties for users to reach the most appropriate and reliable conclusions. Recommendation systems form one of the solutions to deal with the information overload problem by providing personalized services. Using spatial, temporal and social information on recommender systems is a recent trend that increases the performance. Also, taking into account more than one criterion can improve the performance of the recommender systems. In this paper, a location and social network aware recommender system enhanced with multi objective filtering is proposed and described. The results show that the proposed method reaches high coverage while preserving precision. Besides, the proposed method is not affected by the range of ratings and provides persistent results in different settings.