Research Article
Collaborative Recommendation with Energy Distance Correlation
@INPROCEEDINGS{10.1007/978-3-031-28816-6_2, author={Mun Van Dong and Trong Van Nguyen and Nhung Cam Thi Mai and Tu Cam Thi Tran and Hiep Xuan Huynh}, title={Collaborative Recommendation with Energy Distance Correlation}, proceedings={Context-Aware Systems and Applications. 11th EAI International Conference, ICCASA 2022, Vinh Long, Vietnam, October 27-28, 2022, Proceedings}, proceedings_a={ICCASA}, year={2023}, month={3}, keywords={Energy distance Energy dependence measures Collaborative filtering Recommendation system Distance correlation}, doi={10.1007/978-3-031-28816-6_2} }- Mun Van Dong
Trong Van Nguyen
Nhung Cam Thi Mai
Tu Cam Thi Tran
Hiep Xuan Huynh
Year: 2023
Collaborative Recommendation with Energy Distance Correlation
ICCASA
Springer
DOI: 10.1007/978-3-031-28816-6_2
Abstract
The recommendation systems are applied to many fields of the social life. In which, the measure of the similarity, and the measure of the distance are the core problems of the recommender systems, there are many proposals with the different approaches, it shows the characteristics of each recommendation system, commonly used measures such as: the measure Cosine, the measure Pearson, the measure Jaccard, etc. However, there have not been many studies on the energy dependence to determine the correlation of the objects in the process of building a recommendation system. In this article, we mainly focus on determining the correlation/compatibility of the energy-based objects in building a recommendation model. The experimental results are evaluated on two datasets, that are MSWeb datasets and Learning from Sets of Items 2019 datasets, the results show that the proposed model has higher accuracy than the traditional model.
