Social Network-based Recommendation: A Graph Random Walk Kernel Approach

Xin Li; Xin Su; Mengyue Wang

doi:10.1145/2232817.2232915

Social Network-based Recommendation: A Graph Random Walk Kernel Approach

Xin Li
, Xin Su
, Mengyue Wang

Department of Information Systems

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

11 Citations (Scopus)

Abstract

Traditional recommender system research often explores customer, product, and transaction information in providing recommendations. Social relationships in social networks are related to individuals' preferences. This study investigates the product recommendation problem based solely on people's social network information. Taking a kernel-based approach, we capture consumer social influence similarities into a graph random walk kernel and build SVR models to predict consumer opinions. In experiments on a dataset from a movie review website, our proposed model outperforms trust-based models and state-of-the-art graph kernels.

Original language	English
Title of host publication	Proceedings of the 12th ACM/IEEE-CS joint conference on Digital Libraries
Publisher	Association for Computing Machinery
Pages	409-410
ISBN (Print)	9781450311540
DOIs	https://doi.org/10.1145/2232817.2232915
Publication status	Published - Jun 2012
Event	12th ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL '12 - Washington, DC, United States Duration: 10 Jun 2012 → 14 Jun 2012

Conference

Conference	12th ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL '12
Place	United States
City	Washington, DC
Period	10/06/12 → 14/06/12

Research Keywords

graph kernel
random walk
recommendation
social network

Access Output

10.1145/2232817.2232915

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{987e740e57894604a32858c5146986c1,

title = "Social Network-based Recommendation: A Graph Random Walk Kernel Approach",

abstract = "Traditional recommender system research often explores customer, product, and transaction information in providing recommendations. Social relationships in social networks are related to individuals' preferences. This study investigates the product recommendation problem based solely on people's social network information. Taking a kernel-based approach, we capture consumer social influence similarities into a graph random walk kernel and build SVR models to predict consumer opinions. In experiments on a dataset from a movie review website, our proposed model outperforms trust-based models and state-of-the-art graph kernels.",

keywords = "graph kernel, random walk, recommendation, social network",

author = "Xin Li and Xin Su and Mengyue Wang",

year = "2012",

month = jun,

doi = "10.1145/2232817.2232915",

language = "English",

isbn = "9781450311540",

pages = "409--410",

booktitle = "Proceedings of the 12th ACM/IEEE-CS joint conference on Digital Libraries",

publisher = "Association for Computing Machinery",

address = "United States",

note = "12th ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL '12 ; Conference date: 10-06-2012 Through 14-06-2012",

}

Li, X, Su, X & Wang, M 2012, Social Network-based Recommendation: A Graph Random Walk Kernel Approach. in Proceedings of the 12th ACM/IEEE-CS joint conference on Digital Libraries. Association for Computing Machinery, pp. 409-410, 12th ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL '12, Washington, DC, United States, 10/06/12. https://doi.org/10.1145/2232817.2232915

Social Network-based Recommendation: A Graph Random Walk Kernel Approach. / Li, Xin; Su, Xin; Wang, Mengyue.
Proceedings of the 12th ACM/IEEE-CS joint conference on Digital Libraries. Association for Computing Machinery, 2012. p. 409-410.

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

TY - GEN

T1 - Social Network-based Recommendation

T2 - 12th ACM/IEEE-CS Joint Conference on Digital Libraries, JCDL '12

AU - Li, Xin

AU - Su, Xin

AU - Wang, Mengyue

PY - 2012/6

Y1 - 2012/6

N2 - Traditional recommender system research often explores customer, product, and transaction information in providing recommendations. Social relationships in social networks are related to individuals' preferences. This study investigates the product recommendation problem based solely on people's social network information. Taking a kernel-based approach, we capture consumer social influence similarities into a graph random walk kernel and build SVR models to predict consumer opinions. In experiments on a dataset from a movie review website, our proposed model outperforms trust-based models and state-of-the-art graph kernels.

AB - Traditional recommender system research often explores customer, product, and transaction information in providing recommendations. Social relationships in social networks are related to individuals' preferences. This study investigates the product recommendation problem based solely on people's social network information. Taking a kernel-based approach, we capture consumer social influence similarities into a graph random walk kernel and build SVR models to predict consumer opinions. In experiments on a dataset from a movie review website, our proposed model outperforms trust-based models and state-of-the-art graph kernels.

KW - graph kernel

KW - random walk

KW - recommendation

KW - social network

UR - https://www.scopus.com/pages/publications/84863546958

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84863546958&origin=recordpage

U2 - 10.1145/2232817.2232915

DO - 10.1145/2232817.2232915

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

SN - 9781450311540

SP - 409

EP - 410

BT - Proceedings of the 12th ACM/IEEE-CS joint conference on Digital Libraries

PB - Association for Computing Machinery

Y2 - 10 June 2012 through 14 June 2012

ER -

Social Network-based Recommendation: A Graph Random Walk Kernel Approach

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this