Review Open access

Personalized wine recommendations in e-commerce: Integrating knowledge graphs and graph neural networks

J. Liou Zi-Yi Hong Li-Chen Cheng

Aug 2026 · Journal of information science · 0 citations · 46 references

TL;DR

A wine recommendation system based on heterogeneous graph transformers that integrates hybrid node features from users, reviews, and wine knowledge and achieves an average improvement of 2.11% in precision and 5.87% in normalized discounted cumulative gain (NDCG) across top-K recommendations is proposed.

Abstract

This study proposes a wine recommendation system based on heterogeneous graph transformers that integrates hybrid node features from users, reviews, and wine knowledge. We use real-world data from a wine e-commerce platform, including 1685 wines, 12,361 users, 71,507 reviews, and 71,507 ratings. A multi-relational knowledge graph is constructed to represent relationships among wines, customers, and content. Node features are generated via decoding-enhanced BERT with disentangled attention–based review embeddings and structured wine attributes, while the graph structure captures both objective and subjective signals. We evaluate three heterogeneous graph transformer variants and benchmark them against the baseline light graph convolution network model. Our best-performing configuration, heterogeneous graph transformer model C with hybrid features, achieves an average improvement of 2.11% in precision and 5.87% in normalized discounted cumulative gain (NDCG) across top-K recommendations. These results highlight the value of feature diversity and graph-based modeling for enhancing personalized product recommendations in e-commerce.

DOI Semantic Scholar

Read PDF

Similar papers

Open access Sep 2026

A course recommendation method based on bidirectional fusion of graph convolution using knowledge graphs

Knowledge graph–based recommendation systems, such as KGCN, have been widely adopted to alleviate data sparsity and cold-start issues by incorporating auxiliary semantic information. However, most existing methods model either the user side or the item side independently, failing to fully exploit the complementary in...

Jing-Yi Hu, Yi-Wen Zhang, Xi-Qin Ao et al. · Scientific Reports · 0 citations

Oct 2026

RPGCN: A relation-preserving graph convolutional network for enhanced node feature prediction in recommender systems

Sang-Woong Lee, Saqib Ali, Amir Masoud Rahmani et al. · Neural computing & applicati... · 0 citations

#graph neural networks Sep 2026

Co-occurrence graph neural network for recommender systems

A novel neural network called the Co-occurrence Graph Neural Network (CoGNN), which utilizes two co-occurrence graphs to establish user and item relationships and outperforms various baseline models in terms of recommendation accuracy and algorithm convergence.

Chao Lin, Y. Lin, You-Yu Wang et al. · Multimedia Systems · 0 citations

Open access Aug 2026

Research on the Self Evolution Construction and Interpretable Recommendation of Cross Domain Knowledge Graph for E-Commerce Products Based on Multimodal Large Language Model

Cross-domain e-commerce recommendation faces challenges from multimodal product heterogeneity, sparse intercategory associations, and opaque recommendation reasoning. To improve accuracy and interpretability, this study proposes a multimodal large-language-model-driven framework for self-evolving cross-domain product k...

Li Ma, Yuanli Cui · Advanced Electromagnetics · 0 citations

#machine learning Preprint Aug 2026

Neural Regression with Embeddings for Numerical Attribute Prediction in Knowledge Graphs

A neural regression model (LitEm) that enables transductive knowledge graph embedding models to predict numerical attributes within knowledge graphs and a co-training framework that jointly trains state-of-the-art transductive knowledge graph embedding models with LitEm, which improves link prediction performance mainl...

Rupesh Sapkota, Louis Mozart Kamdem Teyou, Moshood Yekini et al. · 0 citations

Conference Aug 2026

A Multi-Perspective Dual-Stream Framework Integrating Transformers and Graph Neural Networks for E-Commerce Opinion Fraud Detection

Online word-of-mouth significantly shapes consumer purchasing decisions in the digital marketplace. However, malicious actors exploit this trust by deploying coordinated fake review campaigns that artificially inflate or deflate product popularity. Traditional detection approaches primarily analyze textual content in i...

Manju Sadasivan, D. A, Shinty P. K. et al. · 2026 International Conferenc... · 0 citations