A Random Walk Based Model Incorporating Social Information for Recommendations

Shang Shang; Sanjeev R. Kulkarni; Paul W. Cuff; Pan Hui

doi:10.1109/MLSP.2012.6349732

A Random Walk Based Model Incorporating Social Information for Recommendations

Shang Shang^*, Sanjeev R. Kulkarni, Paul W. Cuff, Pan Hui

^*Corresponding author for this work

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

23 Citations (Scopus)

Abstract

Collaborative filtering (CF) is one of the most popular approaches to build a recommendation system. In this paper, we propose a hybrid collaborative filtering model based on a Makovian random walk to address the data sparsity and cold start problems in recommendation systems. More precisely, we construct a directed graph whose nodes consist of items and users, together with item content, user profile and social network information. We incorporate user's ratings into edge settings in the graph model. The model provides personalized recommendations and predictions to individuals and groups. The proposed algorithms are evaluated on MovieLens and Epinions datasets. Experimental results show that the proposed methods perform well compared with other graph-based methods, especially in the cold start case.

Original language	English
Title of host publication	2012 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2012
Publisher	IEEE Computer Society
ISBN (Print)	9781467310260
DOIs	https://doi.org/10.1109/MLSP.2012.6349732
Publication status	Published - 2012
Externally published	Yes
Event	2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012 - Santander, Spain Duration: 23 Sept 2012 → 26 Sept 2012

Publication series

Name	IEEE International Workshop on Machine Learning for Signal Processing, MLSP
ISSN (Print)	2161-0363
ISSN (Electronic)	2161-0371

Conference

Conference	2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012
Country/Territory	Spain
City	Santander
Period	23/09/12 → 26/09/12

Keywords

hybrid collaborative filtering model
random walk
Recommendation system
social networks

Access to Document

10.1109/MLSP.2012.6349732

Cite this

Shang, S., Kulkarni, S. R., Cuff, P. W., & Hui, P. (2012). A Random Walk Based Model Incorporating Social Information for Recommendations. In 2012 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2012 Article 6349732 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP). IEEE Computer Society. https://doi.org/10.1109/MLSP.2012.6349732

@inproceedings{5f47021cb03444d2aaacee672ab86c41,

title = "A Random Walk Based Model Incorporating Social Information for Recommendations",

abstract = "Collaborative filtering (CF) is one of the most popular approaches to build a recommendation system. In this paper, we propose a hybrid collaborative filtering model based on a Makovian random walk to address the data sparsity and cold start problems in recommendation systems. More precisely, we construct a directed graph whose nodes consist of items and users, together with item content, user profile and social network information. We incorporate user's ratings into edge settings in the graph model. The model provides personalized recommendations and predictions to individuals and groups. The proposed algorithms are evaluated on MovieLens and Epinions datasets. Experimental results show that the proposed methods perform well compared with other graph-based methods, especially in the cold start case.",

keywords = "hybrid collaborative filtering model, random walk, Recommendation system, social networks",

author = "Shang Shang and Kulkarni, \{Sanjeev R.\} and Cuff, \{Paul W.\} and Pan Hui",

year = "2012",

doi = "10.1109/MLSP.2012.6349732",

language = "English",

isbn = "9781467310260",

series = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",

publisher = "IEEE Computer Society",

booktitle = "2012 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2012",

note = "2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012 ; Conference date: 23-09-2012 Through 26-09-2012",

}

Shang, S, Kulkarni, SR, Cuff, PW & Hui, P 2012, A Random Walk Based Model Incorporating Social Information for Recommendations. in 2012 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2012., 6349732, IEEE International Workshop on Machine Learning for Signal Processing, MLSP, IEEE Computer Society, 2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012, Santander, Spain, 23/09/12. https://doi.org/10.1109/MLSP.2012.6349732

A Random Walk Based Model Incorporating Social Information for Recommendations. / Shang, Shang; Kulkarni, Sanjeev R.; Cuff, Paul W. et al.
2012 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2012. IEEE Computer Society, 2012. 6349732 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - A Random Walk Based Model Incorporating Social Information for Recommendations

AU - Shang, Shang

AU - Kulkarni, Sanjeev R.

AU - Cuff, Paul W.

AU - Hui, Pan

PY - 2012

Y1 - 2012

N2 - Collaborative filtering (CF) is one of the most popular approaches to build a recommendation system. In this paper, we propose a hybrid collaborative filtering model based on a Makovian random walk to address the data sparsity and cold start problems in recommendation systems. More precisely, we construct a directed graph whose nodes consist of items and users, together with item content, user profile and social network information. We incorporate user's ratings into edge settings in the graph model. The model provides personalized recommendations and predictions to individuals and groups. The proposed algorithms are evaluated on MovieLens and Epinions datasets. Experimental results show that the proposed methods perform well compared with other graph-based methods, especially in the cold start case.

AB - Collaborative filtering (CF) is one of the most popular approaches to build a recommendation system. In this paper, we propose a hybrid collaborative filtering model based on a Makovian random walk to address the data sparsity and cold start problems in recommendation systems. More precisely, we construct a directed graph whose nodes consist of items and users, together with item content, user profile and social network information. We incorporate user's ratings into edge settings in the graph model. The model provides personalized recommendations and predictions to individuals and groups. The proposed algorithms are evaluated on MovieLens and Epinions datasets. Experimental results show that the proposed methods perform well compared with other graph-based methods, especially in the cold start case.

KW - hybrid collaborative filtering model

KW - random walk

KW - Recommendation system

KW - social networks

UR - https://www.scopus.com/pages/publications/84870673353

U2 - 10.1109/MLSP.2012.6349732

DO - 10.1109/MLSP.2012.6349732

M3 - Conference Paper published in a book

AN - SCOPUS:84870673353

SN - 9781467310260

T3 - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

BT - 2012 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2012

PB - IEEE Computer Society

T2 - 2012 22nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2012

Y2 - 23 September 2012 through 26 September 2012

ER -

Shang S, Kulkarni SR, Cuff PW, Hui P. A Random Walk Based Model Incorporating Social Information for Recommendations. In 2012 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2012. IEEE Computer Society. 2012. 6349732. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP). doi: 10.1109/MLSP.2012.6349732

A Random Walk Based Model Incorporating Social Information for Recommendations

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this