Geodesic
A new uncertainty-aware similarity for user-based collaborative filtering
Kybernetika, Tome 60 (2024) no. 4, pp. 446-474 Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

User-based Collaborative Filtering (UBCF) is a common approach in Recommender Systems (RS). Essentially, UBCF predicts unprovided entries for the target user by selecting similar neighbors. The effectiveness of UBCF greatly depends on the selected similarity measure and the subsequent choice of neighbors. This paper presents a new Uncertainty-Aware Similarity measure "UASim" which enhances CF by accurately calculating how similar, dissimilar, and uncertain users' preferences are. Uncertainty is a key factor of "UASim" that is managed in the neighborhood selection step of CF. Extensive experimental evaluation, conducted on Flixter, Movielens-100K, and Movielens-1M datasets, indicates that "UASim" shows better performance compared to many representative predefined similarity measures. The proposed measure demonstrates enhancements across various performance indicators, namely: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), coverage, and the F-score.
User-based Collaborative Filtering (UBCF) is a common approach in Recommender Systems (RS). Essentially, UBCF predicts unprovided entries for the target user by selecting similar neighbors. The effectiveness of UBCF greatly depends on the selected similarity measure and the subsequent choice of neighbors. This paper presents a new Uncertainty-Aware Similarity measure "UASim" which enhances CF by accurately calculating how similar, dissimilar, and uncertain users' preferences are. Uncertainty is a key factor of "UASim" that is managed in the neighborhood selection step of CF. Extensive experimental evaluation, conducted on Flixter, Movielens-100K, and Movielens-1M datasets, indicates that "UASim" shows better performance compared to many representative predefined similarity measures. The proposed measure demonstrates enhancements across various performance indicators, namely: Mean Absolute Error (MAE), Root Mean Square Error (RMSE), coverage, and the F-score.
DOI : 10.14736/kyb-2024-4-0446
Classification : 68P10, 68P20, 68T37
Keywords: collaborative filtering; similarity; subjective logic; uncertainty 
@article{10_14736_kyb_2024_4_0446,
     author = {Belmessous, Khadidja and Sebbak, Faouzi and Mataoui, M'hamed and Cherifi, Walid},
     title = {A new uncertainty-aware similarity for user-based collaborative filtering},
     journal = {Kybernetika},
     pages = {446--474},
     year = {2024},
     volume = {60},
     number = {4},
     doi = {10.14736/kyb-2024-4-0446},
     zbl = {07953739},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.14736/kyb-2024-4-0446/}
}
TY  - JOUR
AU  - Belmessous, Khadidja
AU  - Sebbak, Faouzi
AU  - Mataoui, M'hamed
AU  - Cherifi, Walid
TI  - A new uncertainty-aware similarity for user-based collaborative filtering
JO  - Kybernetika
PY  - 2024
SP  - 446
EP  - 474
VL  - 60
IS  - 4
UR  - http://geodesic.mathdoc.fr/articles/10.14736/kyb-2024-4-0446/
DO  - 10.14736/kyb-2024-4-0446
LA  - en
ID  - 10_14736_kyb_2024_4_0446
ER  - 
%0 Journal Article
%A Belmessous, Khadidja
%A Sebbak, Faouzi
%A Mataoui, M'hamed
%A Cherifi, Walid
%T A new uncertainty-aware similarity for user-based collaborative filtering
%J Kybernetika
%D 2024
%P 446-474
%V 60
%N 4
%U http://geodesic.mathdoc.fr/articles/10.14736/kyb-2024-4-0446/
%R 10.14736/kyb-2024-4-0446
%G en
%F 10_14736_kyb_2024_4_0446
Belmessous, Khadidja; Sebbak, Faouzi; Mataoui, M'hamed; Cherifi, Walid. A new uncertainty-aware similarity for user-based collaborative filtering. Kybernetika, Tome 60 (2024) no. 4, pp. 446-474. doi: 10.14736/kyb-2024-4-0446

Cité par Sources :