Explicable recommendation based on knowledge graph

•Explainable recommendation model is proposed to improve recommended performance.•Precision, diversity, novelty and explainability are optimized simultaneously.•The list of candidate recommendation is gained through knowledge graph.•Embedding vectors of entities and relationships are obtained by Tra...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Expert systems with applications Ročník 200; s. 117035
Hlavní autoři: Cai, Xingjuan, Xie, Lijie, Tian, Rui, Cui, Zhihua
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Elsevier Ltd 15.08.2022
Elsevier BV
Témata:
Embedding
Evolutionary algorithms
Explainable recommendation
Genetic algorithms
Knowledge graph
Knowledge representation
Many-objective evolutionary algorithm
Recommendation system
Recommender systems
Unified method
Explainable recommendation
Unified method
Many-objective evolutionary algorithm
Knowledge graph
Recommendation system
ISSN:0957-4174, 1873-6793
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•Explainable recommendation model is proposed to improve recommended performance.•Precision, diversity, novelty and explainability are optimized simultaneously.•The list of candidate recommendation is gained through knowledge graph.•Embedding vectors of entities and relationships are obtained by TransH.•Unified method is used to quantify explainability. Most of the existing researches on recommendation system assemble in how to enhance precision of recommendation, ignoring acceptance and recognition of users. To work out the problem, a model of explainable recommendation on account of knowledge graph as well as many-objective evolutionary algorithm is proposed, which combines recommendation and explanation. In this work, embedding vectors obtained by embedding-based method are used to quantify the explainability, so as to obtain the explainability of paths between users and items. Candidate recommendation list of users is gained from constructed knowledge graph. Many-objective evolutionary algorithm is used to optimize the list of candidate recommendation so as to seek a set of tradeoff solutions to the four objective functions of accuracy, diversity, novelty and explainability. Then, the best path among object user and recommended items is chosen in knowledge graph as the explanation. Finally, the conclusion that can be drawn from various experiments is that the presented model can boost explainability without reducing the precision, diversity as well as novelty.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0957-4174
1873-6793
DOI:10.1016/j.eswa.2022.117035