A Better Understanding of the Interaction Between Users and Items by Knowledge Graph Learning for Temporal Recommendation

Xiao, Chunjing; Xie, Cong; Shuyan, Cao; Zhang, Yuxiang; Fan, Wei; Heng, Hongjun

doi:10.1007/978-3-030-29908-8_11

Cited by 4 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…diseases and symptoms), which may not be identified otherwise. Besides, knowledge graphs enable identifying latent relations between users and items (Xiao et al , 2019a, b; Shi et al , 2020). In our case, we extract features for patient-doctor pairs based on their latent relations in the health knowledge graph.…”

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

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

show abstract

“…Recommender systems are regarded as an essential measure to solve this problem by analyzing the historical data and predicting the user's interest in the items [4]. Nevertheless, most of the existing recommender systems do not consider temporal dynamics, which can affect the accuracy of recommendation [5], [6]. In real-world recommender systems, each user and product tend to go through a distinct series of changes in their characteristics [7].…”

mentioning

confidence: 99%

A Multi-Trans Matrix Factorization Model With Improved Time Weight in Temporal Recommender Systems

Zhang

2020

IEEE Access

View full text Add to dashboard Cite

In real-world recommender systems, users' interest and products' characteristics tend to go through a distinct series of changes over time. Thus, designing a recommender system that can simultaneously track the temporal dynamics of both drifts becomes a significant task. However, most of the existing temporal recommender systems only focus on users' dynamics, ignoring changes in products' characteristics. In this study, we propose a Multi-Trans matrix factorization (MTMF) model with improved time weight to capture temporal dynamics. Firstly, we introduce a personalized time weight that combines the forgetting curve and item similarity to reduce the impact of outdated information and retain the influence of users' stable preferences. Then, we model user and item dynamics by learning the multiple transitions at the userfactor and factor-item latent space between the ongoing time period and all past time periods. Accordingly, we formulate a joint objective function and take a gradient-based alternating optimization algorithm to solve this joint problem. Experimental results on historical datasets MovieLens show that the recommendation accuracy of MTMF with improved time weight is superior to the existing temporal recommendation methods. INDEX TERMS Recommender systems, collaborative filtering, time weight, dynamic preference. I. INTRODUCTION

show abstract

High Order Semantic Relations-Based Temporal Recommendation Model by Collaborative Knowledge Graph Learning

2020

View full text Add to dashboard Cite

A Better Understanding of the Interaction Between Users and Items by Knowledge Graph Learning for Temporal Recommendation

Cited by 4 publications

References 17 publications

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

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

A Multi-Trans Matrix Factorization Model With Improved Time Weight in Temporal Recommender Systems

High Order Semantic Relations-Based Temporal Recommendation Model by Collaborative Knowledge Graph Learning

Contact Info

Product

Resources

About