Merging trust in collaborative filtering to alleviate data sparsity and cold start

Guo, Guibing; Zhang, Jie; Thalmann, Daniel

doi:10.1016/j.knosys.2013.12.007

Cited by 225 publications

(104 citation statements)

References 27 publications

Supporting

Mentioning

104

Contrasting

Order By: Relevance

“…Guo et al [16] have shown that some users are more significant than other users to make recommendations. Suppose W = {1, .…”

Section: Calculation the Significance Of Each Usermentioning

confidence: 99%

“…This issue may deteriorate the performance of trust-based approaches. Hence, like [16] we adopt a weighting factor to devalue trust in a long distance:…”

Section: Aggregating Trusted Neighborsmentioning

confidence: 99%

“…In addition, all users do not have equal significance to make recommendations [18]. Guo et al [16] also noted that making recommendations based on more significant users will result in good accuracy and good coverage. Therefore, it is necessary to consider both significance value, rating similarity and trust value.…”

Section: Incorporating the Ratings Of Trusted Neighborsmentioning

confidence: 99%

See 2 more Smart Citations

Collaborative filtering-based recommender systems by effective trust

Faridani

Jalali

Jahan

2017

Int J Data Sci Anal

View full text Add to dashboard Cite

Collaborative filtering (CF) is one of the most well-known and commonly used techniques to build recommender systems and generate recommendations. However, it suffers from several inherent issues such as data sparsity and cold start. This paper tends to describe the steps based on which the ratings of an active users trusted neighbors are combined to complement and represent the preferences to the active user. First, by discriminating between different users, we calculate the significance of each user to make recommendations. Then, the trusted neighbors of the active user are identified and aggregated. Hence, a new rating profile can be established to represent the preferences of the active user. In the next step, similar users probed based on the new rating profile. Finally, recommendations are generated in the same way as the conventional CF with the difference that if a similar neighbor had not rated the target item, we will predict the value of the target item for this similar neighbor by using the ratings of her directly trusted neighbors and applying MoleTrust algorithm, to combine more similar users to generate a prediction for this target item. Experimental results demonstrate that our method outperforms other counterparts both in terms of accuracy and in terms of coverage.

show abstract

“…Guo et al [16] have shown that some users are more significant than other users to make recommendations. Suppose W = {1, .…”

Section: Calculation the Significance Of Each Usermentioning

confidence: 99%

“…This issue may deteriorate the performance of trust-based approaches. Hence, like [16] we adopt a weighting factor to devalue trust in a long distance:…”

Section: Aggregating Trusted Neighborsmentioning

confidence: 99%

Section: Incorporating the Ratings Of Trusted Neighborsmentioning

confidence: 99%

See 1 more Smart Citation

Collaborative filtering-based recommender systems by effective trust

Faridani

Jalali

Jahan

2017

Int J Data Sci Anal

View full text Add to dashboard Cite

show abstract

“…TidalTrust [24] and MoleTrust [25] incorporated users' trust information into social network traversal-based approaches to get positive recommendation performances. Guo et al [26] merged a user's trusted neighbors' ratings to represent the preferences of the users. Moradi and Ahmadian [27] proposed a reliability-based recommendation method to improve trustaware recommender systems.…”

Section: Related Workmentioning

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

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

“…To overcome such problems, Matrix Factorization methods have been applied extensively by various researchers in the field. [6]- [8]. In recent times, additional sources of information are integrated into RSs.…”

Section: Introductionmentioning

confidence: 99%