Trust Inference Using Implicit Influence for Item Recommendation

Pal, Bithika; Jenamani, Mamata

doi:10.1109/sitis.2017.15

Cited by 4 publications

(15 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In absence of B(θ), t ij comes from the shortest path [9], [11], [12]. Incorporating influence of the intermediate nodes and sometimes going beyond the shortest path actually helps in improving the recommendation accuracy [10]. Now, in this problem setting the main drawback is its scalability.…”

Section: Proposed Path Based Trust Inference Methodologymentioning

confidence: 99%

“…However, none of them considered the individual node influence in the trust inference. In [10], the authors took into account this individual influence in local trust inference. The main intuition in their study is that 'trust more a user if it is already trusted by a larger number of users'.…”

Section: Related Workmentioning

confidence: 99%

“…2) Degree-of-Trustworthiness as Weight: The intuition mentioned in Sec. III-B1 is captured in a metric named degree-oftrustworthiness (δ i ) [10]. The authors define δ i as Equation 3.…”

Section: B Different Types Of Vertex Weight Functionmentioning

confidence: 99%

“…In memory based trust-aware recommendation [7], [8], [10], [12], the rating is predicted in similar to the user-based collab- orative filtering [18]. The trust weight is used in place of useruser similarity score and the weighted average is taken from the user's trusted neighbors inĜ.…”

Section: E Recommendation Using Inferredĝmentioning

confidence: 99%

“…Now, for θ c calculation, c th is chosen Epinions as 1 for indegree as weight and 10 * L max for other two weight functions. For recommendation usingĜ, we perform an offline experiment using leave-one-out mechanism and evaluate the performance using MAE, RMSE and Coverage [10]. These terms are defined as follows,…”

Section: B) Experimental Setupmentioning

confidence: 99%

See 4 more Smart Citations

Threshold-Based Heuristics for Trust Inference in a Social Network

Pal

Banerjee

Jenamani

2018

2018 Eleventh International Conference on Contemporary Computing (IC3)

Self Cite

View full text Add to dashboard Cite

Trust among the users of a social network plays a pivotal role in item recommendation, particularly for the cold start users. Due to the sparse nature of these networks, trust information between any two users may not be always available. To infer the missing trust values, one well-known approach is path based trust estimation, which suggests a user to believe all of its neighbors in the network. In this context, we propose two threshold-based heuristics to overcome the limitation of computation for the path based trust inference. It uses the propagation phenomena of trust and decides a threshold value to select a subset of users for trust propagation. While the first heuristic creates the inferred network considering only the subset of users, the second one is able to preserve the density of the inferred network coming from all users selection. We implement the heuristics and analyze the inferred networks with two real-world datasets. We observe that the proposed threshold based heuristic can recover up to 70 % of the paths with much less time compared to its deterministic counterpart. We also show that the heuristic based inferred trust is capable of preserving the recommendation accuracy.

show abstract

Section: Proposed Path Based Trust Inference Methodologymentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…2) Degree-of-Trustworthiness as Weight: The intuition mentioned in Sec. III-B1 is captured in a metric named degree-oftrustworthiness (δ i ) [10]. The authors define δ i as Equation 3.…”

Section: B Different Types Of Vertex Weight Functionmentioning

confidence: 99%

Section: E Recommendation Using Inferredĝmentioning

confidence: 99%

Section: B) Experimental Setupmentioning

confidence: 99%

See 3 more Smart Citations

Threshold-Based Heuristics for Trust Inference in a Social Network

Pal

Banerjee

Jenamani

2018

2018 Eleventh International Conference on Contemporary Computing (IC3)

Self Cite

View full text Add to dashboard Cite

show abstract

Trust inference using implicit influence and projected user network for item recommendation

Pal

Jenamani

2018

J Intell Inf Syst

View full text Add to dashboard Cite

Double Regularization Matrix Factorization Recommendation Algorithm

Cai

2019

IEEE Access

View full text Add to dashboard Cite

With the development of social networks, the research of integrated social information recommendation models has received extensive attention. However, most existing social recommendation models are based on the matrix factorization technique which ignore the impact of the relationships between items on users' interests, resulting in a decline of recommendation accuracy. To solve this problem, this paper proposes a double regularization matrix factorization recommendation algorithm. The algorithm first uses attribute information and manifold learning to calculate similarity. Then, the matrix factorization model is constrained through the regularization of item association relations and user social relations. Experimental results on real datasets show that the proposed method can effectively alleviate problems such as cold start and data sparsity in the recommender system and improve the recommendation accuracy compared with those of existing methods.

show abstract

Trust Inference Using Implicit Influence for Item Recommendation

Cited by 4 publications

References 23 publications

Threshold-Based Heuristics for Trust Inference in a Social Network

Threshold-Based Heuristics for Trust Inference in a Social Network

Trust inference using implicit influence and projected user network for item recommendation

Double Regularization Matrix Factorization Recommendation Algorithm

Contact Info

Product

Resources

About