Multi-source Information Fusion for Personalized Restaurant Recommendation

Jing Sun; Junming Liu; Yun Xiong; Chu Guan; Yangyong Zhu; Hui Xiong

doi:10.1145/2766462.2767818

Multi-source Information Fusion for Personalized Restaurant Recommendation

Jing Sun
, Junming Liu
, Yun Xiong
, Chu Guan
, Yangyong Zhu
, Hui Xiong

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

17 Citations (Scopus)

Abstract

In this paper, we study the problem of personalized restaurant recommendations. Specifically, we develop a probabilistic factor analysis framework, named RMSQ-MF, which has the ability in exploiting multi-source information, such as the users' task, their friends' preferences, and human mobility patterns, for personalized restaurant recommendations. The rationale of this work is motivated by two observations. First, people's preferences can be affected by their friends. Second, human mobility patterns can reflect the popularity of restaurants to a certain degree. Finally, empirical studies on real-world data demonstrate that the proposed method outperforms benchmark methods with a significant margin.

Original language	English
Title of host publication	SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval
Publisher	Association for Computing Machinery
Pages	983-986
Number of pages	4
ISBN (Electronic)	9781450336215
DOIs	https://doi.org/10.1145/2766462.2767818
Publication status	Published - 9 Aug 2015
Externally published	Yes
Event	38th Annual ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2015) - Santiago, Chile Duration: 9 Aug 2015 → 13 Aug 2015 https://sigir.org/events/past-events/2015-2/

Publication series

Name	SIGIR - Proceedings of the ... International ACM SIGIR Conference on Research and Development in Information Retrieval

Conference

Conference	38th Annual ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2015)
Abbreviated title	SIGIR 2015
Place	Chile
City	Santiago
Period	9/08/15 → 13/08/15
Internet address	https://sigir.org/events/past-events/2015-2/

Funding

This work was supported in part by grants from the National Natural Science Foundation of China under Grant No.61170096,71331005.The work was also partially supported by grants from Shanghai Foundation for Development of Science and Technology under Grant No.13dz2260200 13511504300, 14511107302.

Research Keywords

Bayesian models
Matrix factorization
Mobile computing
Restaurant recommendation

Access Output

10.1145/2766462.2767818

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Sun, J., Liu, J., Xiong, Y., Guan, C., Zhu, Y., & Xiong, H. (2015). Multi-source Information Fusion for Personalized Restaurant Recommendation. In SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 983-986). (SIGIR - Proceedings of the ... International ACM SIGIR Conference on Research and Development in Information Retrieval). Association for Computing Machinery. https://doi.org/10.1145/2766462.2767818

Sun, Jing ; Liu, Junming ; Xiong, Yun et al. / Multi-source Information Fusion for Personalized Restaurant Recommendation. SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, 2015. pp. 983-986 (SIGIR - Proceedings of the ... International ACM SIGIR Conference on Research and Development in Information Retrieval).

@inproceedings{efdc529b42f742e296678b14d918ae5b,

title = "Multi-source Information Fusion for Personalized Restaurant Recommendation",

abstract = "In this paper, we study the problem of personalized restaurant recommendations. Specifically, we develop a probabilistic factor analysis framework, named RMSQ-MF, which has the ability in exploiting multi-source information, such as the users' task, their friends' preferences, and human mobility patterns, for personalized restaurant recommendations. The rationale of this work is motivated by two observations. First, people's preferences can be affected by their friends. Second, human mobility patterns can reflect the popularity of restaurants to a certain degree. Finally, empirical studies on real-world data demonstrate that the proposed method outperforms benchmark methods with a significant margin.",

keywords = "Bayesian models, Matrix factorization, Mobile computing, Restaurant recommendation",

author = "Jing Sun and Junming Liu and Yun Xiong and Chu Guan and Yangyong Zhu and Hui Xiong",

year = "2015",

month = aug,

day = "9",

doi = "10.1145/2766462.2767818",

language = "English",

series = "SIGIR - Proceedings of the ... International ACM SIGIR Conference on Research and Development in Information Retrieval",

publisher = "Association for Computing Machinery",

pages = "983--986",

booktitle = "SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval",

address = "United States",

note = "38th Annual ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2015), SIGIR 2015 ; Conference date: 09-08-2015 Through 13-08-2015",

url = "https://sigir.org/events/past-events/2015-2/",

}

Sun, J, Liu, J, Xiong, Y, Guan, C, Zhu, Y & Xiong, H 2015, Multi-source Information Fusion for Personalized Restaurant Recommendation. in SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR - Proceedings of the ... International ACM SIGIR Conference on Research and Development in Information Retrieval, Association for Computing Machinery, pp. 983-986, 38th Annual ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2015), Santiago, Chile, 9/08/15. https://doi.org/10.1145/2766462.2767818

Multi-source Information Fusion for Personalized Restaurant Recommendation. / Sun, Jing; Liu, Junming; Xiong, Yun et al.
SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, 2015. p. 983-986 (SIGIR - Proceedings of the ... International ACM SIGIR Conference on Research and Development in Information Retrieval).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Multi-source Information Fusion for Personalized Restaurant Recommendation

AU - Sun, Jing

AU - Liu, Junming

AU - Xiong, Yun

AU - Guan, Chu

AU - Zhu, Yangyong

AU - Xiong, Hui

PY - 2015/8/9

Y1 - 2015/8/9

N2 - In this paper, we study the problem of personalized restaurant recommendations. Specifically, we develop a probabilistic factor analysis framework, named RMSQ-MF, which has the ability in exploiting multi-source information, such as the users' task, their friends' preferences, and human mobility patterns, for personalized restaurant recommendations. The rationale of this work is motivated by two observations. First, people's preferences can be affected by their friends. Second, human mobility patterns can reflect the popularity of restaurants to a certain degree. Finally, empirical studies on real-world data demonstrate that the proposed method outperforms benchmark methods with a significant margin.

AB - In this paper, we study the problem of personalized restaurant recommendations. Specifically, we develop a probabilistic factor analysis framework, named RMSQ-MF, which has the ability in exploiting multi-source information, such as the users' task, their friends' preferences, and human mobility patterns, for personalized restaurant recommendations. The rationale of this work is motivated by two observations. First, people's preferences can be affected by their friends. Second, human mobility patterns can reflect the popularity of restaurants to a certain degree. Finally, empirical studies on real-world data demonstrate that the proposed method outperforms benchmark methods with a significant margin.

KW - Bayesian models

KW - Matrix factorization

KW - Mobile computing

KW - Restaurant recommendation

UR - https://www.scopus.com/pages/publications/84953746050

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84953746050&origin=recordpage

U2 - 10.1145/2766462.2767818

DO - 10.1145/2766462.2767818

M3 - RGC 32 - Refereed conference paper (with host publication)

AN - SCOPUS:84953746050

T3 - SIGIR - Proceedings of the ... International ACM SIGIR Conference on Research and Development in Information Retrieval

SP - 983

EP - 986

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

PB - Association for Computing Machinery

T2 - 38th Annual ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2015)

Y2 - 9 August 2015 through 13 August 2015

ER -

Sun J, Liu J, Xiong Y, Guan C, Zhu Y, Xiong H. Multi-source Information Fusion for Personalized Restaurant Recommendation. In SIGIR 2015 - Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery. 2015. p. 983-986. (SIGIR - Proceedings of the ... International ACM SIGIR Conference on Research and Development in Information Retrieval). doi: 10.1145/2766462.2767818

Multi-source Information Fusion for Personalized Restaurant Recommendation

Abstract

Publication series

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this