KJCKorea
Journal Central

@article{ART003399306},
author={Heechan Kim and Yunsuk Kwak and Kim Namgi},
title={Performance Improvement of Recommendation Systems using User Evaluation Information},
journal={Journal of Internet of Things and Convergence},
issn={2466-0078},
year={2026},
volume={12},
number={5},
pages={4}

TY - JOUR
AU - Heechan Kim
AU - Yunsuk Kwak
AU - Kim Namgi
TI - Performance Improvement of Recommendation Systems using User Evaluation Information
JO - Journal of Internet of Things and Convergence
PY - 2026
VL - 12
IS - 5
PB - The Korea Internet of Things Society
SP - 4
EP -
SN - 2466-0078
AB - Existing Graph Signal Processing (GSP)-based recommender systems do not explicitly incorporate user ratings when constructing interaction graphs. We propose Rating-Aware Graph Filtering. The method independently filters interaction-based and rating-based adjacency matrices and combines their outputs through weighted aggregation. Experiments on ML-100K, ML-Latest-Small, ML-1M, and CiaoDVD evaluate F1, MRR, and NDCG using rating thresholds of 2 (Ratings2) and 5 (Ratings5). Compared with HiGSP, Ratings2 improves 23 of 24 dataset-metric comparisons, while Ratings5 improves all 24. However, Ratings2 slightly decreases MRR@10 on ML-1M. These results indicate that user ratings can improve recommendation performance, although gains depend on the dataset, rating threshold, combination weights, and evaluation metric.
KW - Recommendation system;Graph signal processing;Graph filtering;User rating;HiGSP
DO -
UR -
ER -

Heechan Kim, Yunsuk Kwak and Kim Namgi. (2026). Performance Improvement of Recommendation Systems using User Evaluation Information. Journal of Internet of Things and Convergence, 12(5), 4.

Heechan Kim, Yunsuk Kwak and Kim Namgi. 2026, "Performance Improvement of Recommendation Systems using User Evaluation Information", Journal of Internet of Things and Convergence, vol.12, no.5 4.

Heechan Kim, Yunsuk Kwak, Kim Namgi "Performance Improvement of Recommendation Systems using User Evaluation Information" Journal of Internet of Things and Convergence 12.5 4 (2026) : 4.

Heechan Kim, Yunsuk Kwak, Kim Namgi. Performance Improvement of Recommendation Systems using User Evaluation Information. 2026; 12(5), 4.

Heechan Kim, Yunsuk Kwak and Kim Namgi. "Performance Improvement of Recommendation Systems using User Evaluation Information" Journal of Internet of Things and Convergence 12, no.5 (2026) : 4.

Heechan Kim; Yunsuk Kwak; Kim Namgi. Performance Improvement of Recommendation Systems using User Evaluation Information. Journal of Internet of Things and Convergence, 12(5), 4.

Heechan Kim; Yunsuk Kwak; Kim Namgi. Performance Improvement of Recommendation Systems using User Evaluation Information. Journal of Internet of Things and Convergence. 2026; 12(5) 4.

Heechan Kim, Yunsuk Kwak, Kim Namgi. Performance Improvement of Recommendation Systems using User Evaluation Information. 2026; 12(5), 4.

Heechan Kim, Yunsuk Kwak and Kim Namgi. "Performance Improvement of Recommendation Systems using User Evaluation Information" Journal of Internet of Things and Convergence 12, no.5 (2026) : 4.