About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Collaborative Computing: Networking, Applications and Worksharing. 13th International Conference, CollaborateCom 2017, Edinburgh, UK, December 11–13, 2017, Proceedings

Research Article

A Point of Interest Recommendation Approach by Fusing Geographical and Reputation Influence on Location Based Social Networks

Download(Requires a free EAI acccount)
140 downloads
Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-030-00916-8_22,
        author={Jun Zeng and Feng Li and Junhao Wen and Wei Zhou},
        title={A Point of Interest Recommendation Approach by Fusing Geographical and Reputation Influence on Location Based Social Networks},
        proceedings={Collaborative Computing: Networking, Applications and Worksharing. 13th International Conference, CollaborateCom 2017, Edinburgh, UK, December 11--13, 2017, Proceedings},
        proceedings_a={COLLABORATECOM},
        year={2018},
        month={10},
        keywords={POI recommendation Collaborative filtering Location-based social networks Geographical influence},
        doi={10.1007/978-3-030-00916-8_22}
    }
    
  • Jun Zeng
    Feng Li
    Junhao Wen
    Wei Zhou
    Year: 2018
    A Point of Interest Recommendation Approach by Fusing Geographical and Reputation Influence on Location Based Social Networks
    COLLABORATECOM
    Springer
    DOI: 10.1007/978-3-030-00916-8_22
Jun Zeng1,*, Feng Li1,*, Junhao Wen1,*, Wei Zhou1,*
  • 1: Chongqing University
*Contact email: zengjun@cqu.edu.cn, lifeng@cqu.edu.cn, jhwen@cqu.edu.cn, zhouwei@cqu.edu.cn

Abstract

With the rapid development of location-based social networks (LBSNs), more and more people form the habit of sharing locations with their friends. Point of interest (POI) recommendation is aiming to recommend new places for users when they explore their surroundings. How to make proper recommendation has been a key point on the basis of existing information. In this paper, we propose a novel POI recommendation approach by fusing user preference, geographical influence and social reputation. TFIDF is used to represent user preference. Then, we further improve recommendation model by incorporating geographical distance and popularity. In the dataset, we find friends in LBSNs share low common visited POIs. Instead of directly getting recommendation from friends, users attain recommendation from others according to their reputation in the LBSNs. Finally, experimental results on real-world dataset demonstrate that the proposed method performs much better than other recommendation methods.

Keywords
POI recommendation Collaborative filtering Location-based social networks Geographical influence
Published
2018-10-17
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-030-00916-8_22
Copyright © 2017–2025 EAI
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL