Context-aware point-of-interest recommendation using Tensor Factorization with social regularization

Lina Yao, Quan Z. Sheng, Yongrui Qin, Xianzhi Wang, Ali Shemshadi, Qi He

Research output: Chapter in Book/Report/Conference proceedingConference contribution

47 Citations (Scopus)

Abstract

Point-of-Interest (POI) recommendation is a new type of recommendation task that comes along with the prevalence of locationbased social networks in recent years. Compared with traditional tasks, it focuses more on personalized, context-aware recommendation results to provide better user experience. To address this new challenge, we propose a Collaborative Filtering method based on Nonnegative Tensor Factorization, a generalization of the Matrix Factorization approach that exploits a high-order tensor instead of traditional User-Location matrix to model multi-dimensional contextual information. The factorization of this tensor leads to a compact model of the data which is specially suitable for context-aware POI recommendations. In addition, we fuse users' social relations as regularization terms of the factorization to improve the recommendation accuracy. Experimental results on real-world datasets demonstrate the effectiveness of our approach.

Original languageEnglish
Title of host publicationSIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval
PublisherAssociation for Computing Machinery, Inc
Pages1007-1010
Number of pages4
ISBN (Electronic)9781450336215
DOIs
Publication statusPublished - 9 Aug 2015
Externally publishedYes
Event38th International ACM SIGIR Conference on Research and Development in Information Retrieval - Santiago, Chile
Duration: 9 Aug 201513 Aug 2015
Conference number: 38

Conference

Conference38th International ACM SIGIR Conference on Research and Development in Information Retrieval
Abbreviated titleSIGIR 2015
CountryChile
CitySantiago
Period9/08/1513/08/15

Fingerprint

Factorization
Tensors
Collaborative filtering
Electric fuses

Cite this

Yao, L., Sheng, Q. Z., Qin, Y., Wang, X., Shemshadi, A., & He, Q. (2015). Context-aware point-of-interest recommendation using Tensor Factorization with social regularization. In SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 1007-1010). Association for Computing Machinery, Inc. https://doi.org/10.1145/2766462.2767794
Yao, Lina ; Sheng, Quan Z. ; Qin, Yongrui ; Wang, Xianzhi ; Shemshadi, Ali ; He, Qi. / Context-aware point-of-interest recommendation using Tensor Factorization with social regularization. SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc, 2015. pp. 1007-1010
@inproceedings{22512d5f18554feda6de76d2f1527c0f,
title = "Context-aware point-of-interest recommendation using Tensor Factorization with social regularization",
abstract = "Point-of-Interest (POI) recommendation is a new type of recommendation task that comes along with the prevalence of locationbased social networks in recent years. Compared with traditional tasks, it focuses more on personalized, context-aware recommendation results to provide better user experience. To address this new challenge, we propose a Collaborative Filtering method based on Nonnegative Tensor Factorization, a generalization of the Matrix Factorization approach that exploits a high-order tensor instead of traditional User-Location matrix to model multi-dimensional contextual information. The factorization of this tensor leads to a compact model of the data which is specially suitable for context-aware POI recommendations. In addition, we fuse users' social relations as regularization terms of the factorization to improve the recommendation accuracy. Experimental results on real-world datasets demonstrate the effectiveness of our approach.",
keywords = "Location based social networks, Recommendation, Social regularization, Tensor Factorization",
author = "Lina Yao and Sheng, {Quan Z.} and Yongrui Qin and Xianzhi Wang and Ali Shemshadi and Qi He",
year = "2015",
month = "8",
day = "9",
doi = "10.1145/2766462.2767794",
language = "English",
pages = "1007--1010",
booktitle = "SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval",
publisher = "Association for Computing Machinery, Inc",

}

Yao, L, Sheng, QZ, Qin, Y, Wang, X, Shemshadi, A & He, Q 2015, Context-aware point-of-interest recommendation using Tensor Factorization with social regularization. in SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc, pp. 1007-1010, 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, Santiago, Chile, 9/08/15. https://doi.org/10.1145/2766462.2767794

Context-aware point-of-interest recommendation using Tensor Factorization with social regularization. / Yao, Lina; Sheng, Quan Z.; Qin, Yongrui; Wang, Xianzhi; Shemshadi, Ali; He, Qi.

SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc, 2015. p. 1007-1010.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Context-aware point-of-interest recommendation using Tensor Factorization with social regularization

AU - Yao, Lina

AU - Sheng, Quan Z.

AU - Qin, Yongrui

AU - Wang, Xianzhi

AU - Shemshadi, Ali

AU - He, Qi

PY - 2015/8/9

Y1 - 2015/8/9

N2 - Point-of-Interest (POI) recommendation is a new type of recommendation task that comes along with the prevalence of locationbased social networks in recent years. Compared with traditional tasks, it focuses more on personalized, context-aware recommendation results to provide better user experience. To address this new challenge, we propose a Collaborative Filtering method based on Nonnegative Tensor Factorization, a generalization of the Matrix Factorization approach that exploits a high-order tensor instead of traditional User-Location matrix to model multi-dimensional contextual information. The factorization of this tensor leads to a compact model of the data which is specially suitable for context-aware POI recommendations. In addition, we fuse users' social relations as regularization terms of the factorization to improve the recommendation accuracy. Experimental results on real-world datasets demonstrate the effectiveness of our approach.

AB - Point-of-Interest (POI) recommendation is a new type of recommendation task that comes along with the prevalence of locationbased social networks in recent years. Compared with traditional tasks, it focuses more on personalized, context-aware recommendation results to provide better user experience. To address this new challenge, we propose a Collaborative Filtering method based on Nonnegative Tensor Factorization, a generalization of the Matrix Factorization approach that exploits a high-order tensor instead of traditional User-Location matrix to model multi-dimensional contextual information. The factorization of this tensor leads to a compact model of the data which is specially suitable for context-aware POI recommendations. In addition, we fuse users' social relations as regularization terms of the factorization to improve the recommendation accuracy. Experimental results on real-world datasets demonstrate the effectiveness of our approach.

KW - Location based social networks

KW - Recommendation

KW - Social regularization

KW - Tensor Factorization

UR - http://www.scopus.com/inward/record.url?scp=84953774751&partnerID=8YFLogxK

U2 - 10.1145/2766462.2767794

DO - 10.1145/2766462.2767794

M3 - Conference contribution

SP - 1007

EP - 1010

BT - SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval

PB - Association for Computing Machinery, Inc

ER -

Yao L, Sheng QZ, Qin Y, Wang X, Shemshadi A, He Q. Context-aware point-of-interest recommendation using Tensor Factorization with social regularization. In SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, Inc. 2015. p. 1007-1010 https://doi.org/10.1145/2766462.2767794