A matrix factorization technique with trust propagation for recommendation in social networks

Jamali, Mohsen; Ester, Martin

doi:10.1145/1864708.1864736

Cited by 1,348 publications

(840 citation statements)

References 11 publications

Supporting

Mentioning

834

Contrasting

Unclassified

Order By: Relevance

“…Therefore, many recommendation methods have begun to focus on how to use social information to improve the quality of recommendation in recent years. Some representative work such as SoRec [22] and SocialMF [23] combined the matrix factorization method with social information to improve recommendation accuracy. TidalTrust [24] and MoleTrust [25] incorporated users' trust information into social network traversal-based approaches to get positive recommendation performances.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Using Trust of Social Ties for Recommendation

Chen

Shao

Zhu

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYNowadays, with the development of online social networks (OSN), a mass of online social information has been generated in OSN, which has triggered research on social recommendation. Collaborative filtering, as one of the most popular techniques in social recommendation, faces several challenges, such as data sparsity, cold-start users and prediction quality. The motivation of our work is to deal with the above challenges by effectively combining collaborative filtering technology with social information. The trust relationship has been identified as a useful means of using social information to improve the quality of recommendation. In this paper, we propose a trust-based recommendation approach which uses GlobalTrust (GT) to represent the trust value among users as neighboring nodes. A matrix factorization based on singular value decomposition is used to get a trust network built on the GT value. The recommendation results are obtained through a modified random walk algorithm called GlobalTrustWalker. Through experiments on a real-world sparser dataset, we demonstrate that the proposed approach can better utilize users' social trust information and improve the recommendation accuracy on coldstart users. key words: social network, trust-based, collaborative filtering, random walk

show abstract

Section: Related Workmentioning

confidence: 99%

“…Jamali and Ester [12] combined the trust propagation mechanism in the social network with the matrix decomposition model to improve the recommendation quality. The trust relationship from social information has been identified as a useful means of using social information to improve the quality of recommendation.…”

Section: Introductionmentioning

confidence: 99%

Using Trust of Social Ties for Recommendation

Chen

Shao

Zhu

et al. 2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Matrix factorization has been used for form model for recommendation. Use breadth first and shortest path algorithm for trust value calculation [8].…”

Section: B Literature Reviewmentioning

confidence: 99%

“…One of the main techniques in the personalized [6][8] [15] rating prediction is matrix factorization . Matrix factorization extracts the user item rating matrix and recommends based on the similarity of the user who given same rating to the single item [8]. This system simply calculates average between item ratings and predict as a recommendation.…”

Section: Introductionmentioning

confidence: 99%

Survey on Quality of Service Recommendation

Jadhav¹,

Satpute²

2016

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Tremendous popularity of the ecommerce applications increased now days. Numerous amounts of reviews and ratings are available on the sites. Such as comments, reviews description of the local service. This type of information is valuable for the new user who judges the product online to make their decision. Sometimes this information may be having problem to recommend user about product recommendation because of the lack of reviews and rating of particular product. If any product has two rating one 5 and other is 2 they only have two ratings. So while recommending this product just finds average of ratings and show to user. This not provides quality of service of the recommendation. This is not enough to extract public opinions. To provide quality of service to the recommendation have to improve overall evaluation of rating. Find the trust of the user service rating and feature. Extract the overall rating and trust of service by combining the service rating to providing quality of service.

show abstract

“…To solve these problems some scholars integrated clustering methods with traditional collaborative filtering algorithms [2][3][4]. Other scholars began to apply user trust to recommend algorithm [5][6][7][8][9]. Although these methods can relieve the sparsity and improve the accuracy of predictions to some extent, they still needs user-item matrix to measure the similarity.…”

Section: Introductionmentioning

confidence: 99%

A Collaborative Filtering Algorithm Based on Double Clustering and User Trust

Tang¹,

Li²

2016

Proceedings of the 2016 International Conference on Sensor Network and Computer Engineering

View full text Add to dashboard Cite

Abstract.A collaborative filtering algorithm based on double clustering and user trust to solve data sparse and cold start problem is present. This algorithm uses user-clustering matrix to measure the user's degree of similarity, which could reduce the dimension of the user-item matrix. On the other hand it uses user level trust to perform predictions in rating predicting step. The experiments results show that this method could relieve the sparsity problem and improve the accuracy of the prediction results.

show abstract

A matrix factorization technique with trust propagation for recommendation in social networks

Cited by 1,348 publications

References 11 publications

Using Trust of Social Ties for Recommendation

Using Trust of Social Ties for Recommendation

Survey on Quality of Service Recommendation

A Collaborative Filtering Algorithm Based on Double Clustering and User Trust

Contact Info

Product

Resources

About