Personalized Recommendation Method of POI Based on Deep Neural Network

Yuan Gao; Zhizhou Duan; Weifeng Shi; Jun Feng; Yao Yi Chiang

doi:10.1109/BESC48373.2019.8963449

Personalized Recommendation Method of POI Based on Deep Neural Network

Yuan Gao, Zhizhou Duan, Weifeng Shi, Jun Feng, Yao Yi Chiang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Scopus citations

Abstract

With the rapid development of Location-based social networks (LBSN), there is a growing demand for location services. How to use the users' historical check-in data for exploring their visit patterns and preference characteristics to realize personalized point-of-interest (POI) recommendation has become an important topic. Finding valid features from the check-in data is the key to POI recommendation. Deep learning is a multi-level representation learning method, which can better explore the relationship between features. Therefore, a new POI recommendation model named DLM based on deep neural network is proposed in this paper. This model incorporates topic features, user preference features and geographical factor features in the LBSN into the POI recommendation tasks, thereby it improves the efficiency of users' personalized POI recommendation. A lot of experiments on public data set Foursquare have proved the advantages and effectiveness of the proposed method.

Original language	English (US)
Title of host publication	BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728147628
DOIs	https://doi.org/10.1109/BESC48373.2019.8963449
State	Published - Oct 2019
Externally published	Yes
Event	6th International Conference on Behavioral, Economic and Socio-Cultural Computing, BESC 2019 - Beijing, China Duration: Oct 28 2019 → Oct 30 2019

Publication series

Name	BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings

Conference

Conference	6th International Conference on Behavioral, Economic and Socio-Cultural Computing, BESC 2019
Country/Territory	China
City	Beijing
Period	10/28/19 → 10/30/19

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This work is supported by the MOE(Ministry of Education in China) project of Humanities and Social Sciences 18YJA630025.

Publisher Copyright:
© 2019 IEEE.

Keywords

Deep Learning
LBSN
POI recommendation

Publisher link

10.1109/BESC48373.2019.8963449

Find It

Find It at U of M Libraries

Cite this

Gao, Y., Duan, Z., Shi, W., Feng, J., & Chiang, Y. Y. (2019). Personalized Recommendation Method of POI Based on Deep Neural Network. In BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings Article 8963449 (BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BESC48373.2019.8963449

Personalized Recommendation Method of POI Based on Deep Neural Network. / Gao, Yuan; Duan, Zhizhou; Shi, Weifeng et al.
BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8963449 (BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Gao, Y, Duan, Z, Shi, W, Feng, J & Chiang, YY 2019, Personalized Recommendation Method of POI Based on Deep Neural Network. in BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings., 8963449, BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings, Institute of Electrical and Electronics Engineers Inc., 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, BESC 2019, Beijing, China, 10/28/19. https://doi.org/10.1109/BESC48373.2019.8963449

Gao Y, Duan Z, Shi W, Feng J, Chiang YY. Personalized Recommendation Method of POI Based on Deep Neural Network. In BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8963449. (BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings). doi: 10.1109/BESC48373.2019.8963449

Gao, Yuan ; Duan, Zhizhou ; Shi, Weifeng et al. / Personalized Recommendation Method of POI Based on Deep Neural Network. BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings).

@inproceedings{de40756cd5c946cfb00cd22184a3996b,

title = "Personalized Recommendation Method of POI Based on Deep Neural Network",

abstract = "With the rapid development of Location-based social networks (LBSN), there is a growing demand for location services. How to use the users' historical check-in data for exploring their visit patterns and preference characteristics to realize personalized point-of-interest (POI) recommendation has become an important topic. Finding valid features from the check-in data is the key to POI recommendation. Deep learning is a multi-level representation learning method, which can better explore the relationship between features. Therefore, a new POI recommendation model named DLM based on deep neural network is proposed in this paper. This model incorporates topic features, user preference features and geographical factor features in the LBSN into the POI recommendation tasks, thereby it improves the efficiency of users' personalized POI recommendation. A lot of experiments on public data set Foursquare have proved the advantages and effectiveness of the proposed method.",

keywords = "Deep Learning, LBSN, POI recommendation",

author = "Yuan Gao and Zhizhou Duan and Weifeng Shi and Jun Feng and Chiang, {Yao Yi}",

note = "Funding Information: ACKNOWLEDGMENT This work is supported by the MOE(Ministry of Education in China) project of Humanities and Social Sciences 18YJA630025. Publisher Copyright: {\textcopyright} 2019 IEEE.; 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, BESC 2019 ; Conference date: 28-10-2019 Through 30-10-2019",

year = "2019",

month = oct,

doi = "10.1109/BESC48373.2019.8963449",

language = "English (US)",

series = "BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings",

}

TY - GEN

T1 - Personalized Recommendation Method of POI Based on Deep Neural Network

AU - Gao, Yuan

AU - Duan, Zhizhou

AU - Shi, Weifeng

AU - Feng, Jun

AU - Chiang, Yao Yi

PY - 2019/10

Y1 - 2019/10

N2 - With the rapid development of Location-based social networks (LBSN), there is a growing demand for location services. How to use the users' historical check-in data for exploring their visit patterns and preference characteristics to realize personalized point-of-interest (POI) recommendation has become an important topic. Finding valid features from the check-in data is the key to POI recommendation. Deep learning is a multi-level representation learning method, which can better explore the relationship between features. Therefore, a new POI recommendation model named DLM based on deep neural network is proposed in this paper. This model incorporates topic features, user preference features and geographical factor features in the LBSN into the POI recommendation tasks, thereby it improves the efficiency of users' personalized POI recommendation. A lot of experiments on public data set Foursquare have proved the advantages and effectiveness of the proposed method.

AB - With the rapid development of Location-based social networks (LBSN), there is a growing demand for location services. How to use the users' historical check-in data for exploring their visit patterns and preference characteristics to realize personalized point-of-interest (POI) recommendation has become an important topic. Finding valid features from the check-in data is the key to POI recommendation. Deep learning is a multi-level representation learning method, which can better explore the relationship between features. Therefore, a new POI recommendation model named DLM based on deep neural network is proposed in this paper. This model incorporates topic features, user preference features and geographical factor features in the LBSN into the POI recommendation tasks, thereby it improves the efficiency of users' personalized POI recommendation. A lot of experiments on public data set Foursquare have proved the advantages and effectiveness of the proposed method.

KW - Deep Learning

KW - LBSN

KW - POI recommendation

UR - http://www.scopus.com/inward/record.url?scp=85079069695&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85079069695&partnerID=8YFLogxK

U2 - 10.1109/BESC48373.2019.8963449

DO - 10.1109/BESC48373.2019.8963449

M3 - Conference contribution

AN - SCOPUS:85079069695

T3 - BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings

BT - BESC 2019 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 6th International Conference on Behavioral, Economic and Socio-Cultural Computing, BESC 2019

Y2 - 28 October 2019 through 30 October 2019

ER -

Personalized Recommendation Method of POI Based on Deep Neural Network

Abstract

Publication series

Conference

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this