Bridging the gap between linked open data-based recommender systems and distributed representations

Basile, Pierpaolo; Greco, Claudio; Suglia, Alessandro; Semeraro, Giovanni

doi:10.1016/j.is.2019.07.001

Cited by 7 publications

(8 citation statements)

References 26 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing research generally uses contextual information with latent factor methods, especially MF, to achieve the relationship between users and items [Basile et al,2019]. The recommendation algorithm presented a multidimensional approach through the scattered linear method and MF [Sun et al,2020].…”

Section: Hybridmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Objective Entropy FCSVD: Contextual Spectrum Analysis for Prototyping Recommender Systems

Mirabedini

Rodpysh

Banirostam

2022

Preprint

View full text Add to dashboard Cite

In recent years explosive increase and variety of information due to the progress of the internet. Therefore, decision making in different fields has faced different challenges. Recommender systems provide personalized services to users by identifying users' interests, filtering information, and managing information, especially contextual information. Similarity criteria based on contextual information is a way to reduce the challenge of starting a cold. We argue that similarity is a vague concept, and we more realistic results in recommender systems using fuzzy logic. Applying fuzzy logic to contextual information can be an effective way to identify ambiguities and uncertainties in measuring the similarity of items and users. In this paper, we present a new multilevel contextual fuzzy similarity criterion with SVD matrix for recommending systems called FCSVD Which is based on a combination of similarity criteria PSS, fuzzy rules and contextual information. The results show an improvement in the accuracy of the method recommendations FVSVD compared to the CACF, CTLSVD, MF-LOD and CFSVD methods according to evaluation measure Precision, Recall, F1-score.

show abstract

Section: Hybridmentioning

confidence: 99%

“…Finally, a single value decomposition matrix called FCSVD is presented. Regarding that, formula (12) calculates the actual value of r uic . The approximate rate of user u to item i with c context is the actual value of r uic .…”

Section: Context Similarity Singular Value Decomposition (Fcsvd)mentioning

confidence: 99%

Multi-Objective Entropy FCSVD: Contextual Spectrum Analysis for Prototyping Recommender Systems

Mirabedini

Rodpysh

Banirostam

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Existing knowledge graph-based recommendation methods can be classified into embedding-based and path-based methods. The former methods incorporate a knowledge graph into the recommendation by learning representations of entities and relations in the knowledge graph and then incorporating the learned representations into a recommendation framework (Basile et al , 2019; Cao et al , 2019; He et al , 2019; Ren et al , 2019). The latter methods use explicit connections between entities in a knowledge graph to enrich profiles by adding relevant entities or to measure entity similarities by using graph analysis techniques (Chaudhari et al , 2017; Deng et al , 2019; Pla Karidi et al , 2018).…”

Section: Theoretical Background and Literature Reviewmentioning

confidence: 99%

Doctor recommendation on healthcare consultation platforms: an integrated framework of knowledge graph and deep learning

Yuan

Deng

2021

INTR

View full text Add to dashboard Cite

PurposeRecommending suitable doctors to patients on healthcare consultation platforms is important to both the patients and the platforms. Although doctor recommendation methods have been proposed, they failed to explain recommendations and address the data sparsity problem, i.e. most patients on the platforms are new and provide little information except disease descriptions. This research aims to develop an interpretable doctor recommendation method based on knowledge graph and interpretable deep learning techniques to fill the research gaps.Design/methodology/approachThis research proposes an advanced doctor recommendation method that leverages a health knowledge graph to overcome the data sparsity problem and uses deep learning techniques to generate accurate and interpretable recommendations. The proposed method extracts interactive features from the knowledge graph to indicate implicit interactions between patients and doctors and identifies individual features that signal the doctors' service quality. Then, the authors feed the features into a deep neural network with layer-wise relevance propagation to generate readily usable and interpretable recommendation results.FindingsThe proposed method produces more accurate recommendations than diverse baseline methods and can provide interpretations for the recommendations.Originality/valueThis study proposes a novel doctor recommendation method. Experimental results demonstrate the effectiveness and robustness of the method in generating accurate and interpretable recommendations. The research provides a practical solution and some managerial implications to online platforms that confront information overload and transparency issues.

show abstract

“…Collaborative (CL) systems make recommendations based on groups of users with similar preferences. The similarity between users is normally computed by comparing the ratings that they give to some of the items [66]. Next, the results obtained over the MovieLens 1M and MovieLens 10M datasets are shown in Figures 5 and 6.…”

Section: -3-comparison Of Utv To Other Recommender System Modelsmentioning

confidence: 99%

“…The results obtained over both datasets on all the four examined criteria suggest the higher efficiency of UTV than that of the other recommender system algorithms. In this subsection, the method presented in this research is compared to a number of other models presented for recommender systems based on the RMSE and Accuracy criteria over MovieLens 1M and MovieLens 10M, as follows: In the paper [66], authors propose a Content-based Recommender System that exploits knowledge graph embedding for representing items. The embedding are built by leveraging on triples extracted from Wikidata and their approach for computing a user profile based on knowledge base embedding.…”

Section: -3-comparison Of Utv To Other Recommender System Modelsmentioning

confidence: 99%

Presentation of a recommender system with ensemble learning and graph embedding: a case on MovieLens

Forouzandeh

Berahmand

Rostami

2020

Multimed Tools Appl

View full text Add to dashboard Cite

Information technology has spread widely, and extraordinarily large amounts of data have been made accessible to users, which has made it challenging to select data that are in accordance with user needs. For the resolution of the above issue, recommender systems have emerged, which much help users go through the process of decision-making and selecting relevant data. A recommender system predicts users' behavior to be capable of detecting their interests and needs, and it often uses the classification technique for this purpose. It may not be sufficiently accurate to employ individual classification, where not all cases can be examined, which makes the method inappropriate to specific problems. In this research, group classification and the ensemble learning technique were used for increasing prediction accuracy in recommender systems. Another issue that is raised here concerns user analysis. Given the large size of the data and a large number of users, the process of user needs analysis and prediction (using a graph in most cases, representing the relations between users and their selected items) is complicated and cumbersome in recommender systems. Graph embedding was also proposed for resolution of this issue, where all or part of user behavior can be simulated through the generation of several vectors, resolving the problem of user behavior analysis to a large extent while maintaining high efficiency. In this research, individuals most similar to the target user were classified using ensemble learning, fuzzy rules, and the decision tree, and relevant recommendations were then made to each user with a heterogeneous knowledge graph and embedding vectors. This study was performed on the MovieLens datasets, and the obtained results indicated the high efficiency of the presented method.

show abstract

Bridging the gap between linked open data-based recommender systems and distributed representations

Cited by 7 publications

References 26 publications

Multi-Objective Entropy FCSVD: Contextual Spectrum Analysis for Prototyping Recommender Systems

Multi-Objective Entropy FCSVD: Contextual Spectrum Analysis for Prototyping Recommender Systems

Doctor recommendation on healthcare consultation platforms: an integrated framework of knowledge graph and deep learning

Presentation of a recommender system with ensemble learning and graph embedding: a case on MovieLens

Contact Info

Product

Resources

About