Multiple Similar Groups Based Information Technology for POI Recommendation in LBSNs

DOI

10.2991/978-94-6463-108-1_45How to use a DOI?

Keywords

Modern information technology; Point-of-interest; recommendation system; information overload; similarity measurement; collaborative filtering

Abstract

With the development of modern information technology, it becomes increasingly easier for users to obtain information through various type of services or applications. However, it also brings difficulty for users to search for really desired information among massive corresponding data. Thus, recommendation systems have become necessary for these services and applications to solve the information overload problem. Point-of-interest (POI) recommendation is famous in Location-based social networks (LBSN) for the ability of exploring users’ preference and recommending interesting places. Most traditional POI recommendation algorithms are collaborative filtering (CF) based, and the key idea is to generate recommendation list for a target user by mining historical data of his similar users. We found that, different similarity measurement method may lead to different conclusions. Thus, we proposed a multiple similar group-based CF algorithm for POI recommendation in this paper. Given a target user, we first determined his similar users by using different similarity calculation methods and constructed corresponding groups. The recommended locations for the target user are determined by comprehensively considering the suggestions of our groups. We implemented our algorithm and compared with previous approaches by using the dataset. The experimental results show that, our algorithm performs best.

Copyright

© 2022 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yibo Ding
AU  - Jinyu Bai
AU  - Yiqing Dai
AU  - Jinshuo Zhang
AU  - Yixuan Zheng
AU  - Qitai Xu
AU  - Shengwen Yu
PY  - 2022
DA  - 2022/12/30
TI  - Multiple Similar Groups Based Information Technology for POI Recommendation in LBSNs
BT  - Proceedings of the 2022 International Conference on Computer Science, Information Engineering and Digital Economy (CSIEDE 2022)
PB  - Atlantis Press
SP  - 397
EP  - 404
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-108-1_45
DO  - 10.2991/978-94-6463-108-1_45
ID  - Ding2022
ER  -