Geodesic
Audio Feature-based User Profiles for Personalized Music Recommendation: A Dataset-driven Evaluation
Computer Science and Information Systems, Tome 23 (2026) no. 1

Voir la notice de l'article provenant de la source Computer Science and Information Systems website

In this paper, we propose an experimental content-based track recommendation system, which relies on an aggregated features which considers audio feature values from Spotify Data Catalog, track lyrics and popularity ratings. As system evaluation protocol, we evaluate how relevant the top-5 recommended tracks are to the user profile, which is based on average audio feature (danceability, energy, valence, loudness, instrumentalness, liveness, speechiness and acousticness) values from the user’s listening history. Based on the evaluation results, we come to the conclusion that the recommended tracks are similar to the user’s profile.
Keywords: recommender systems, pca, k-means, aggregated feature, mean absolute error 
Ionuţ-Dragoş Neremzoiu; Andreea Liliana Bădică. Audio Feature-based User Profiles for Personalized Music Recommendation: A Dataset-driven Evaluation. Computer Science and Information Systems, Tome 23 (2026) no. 1. http://geodesic.mathdoc.fr/item/CSIS_2026_23_1_a26/
@article{CSIS_2026_23_1_a26,
     author = {Ionu\c{t}-Drago\c{s} Neremzoiu and Andreea Liliana B\u{a}dic\u{a}},
     title = {Audio {Feature-based} {User} {Profiles} for {Personalized} {Music} {Recommendation:} {A} {Dataset-driven} {Evaluation}},
     journal = {Computer Science and Information Systems},
     year = {2026},
     volume = {23},
     number = {1},
     url = {http://geodesic.mathdoc.fr/item/CSIS_2026_23_1_a26/}
}
TY  - JOUR
AU  - Ionuţ-Dragoş Neremzoiu
AU  - Andreea Liliana Bădică
TI  - Audio Feature-based User Profiles for Personalized Music Recommendation: A Dataset-driven Evaluation
JO  - Computer Science and Information Systems
PY  - 2026
VL  - 23
IS  - 1
UR  - http://geodesic.mathdoc.fr/item/CSIS_2026_23_1_a26/
ID  - CSIS_2026_23_1_a26
ER  - 
%0 Journal Article
%A Ionuţ-Dragoş Neremzoiu
%A Andreea Liliana Bădică
%T Audio Feature-based User Profiles for Personalized Music Recommendation: A Dataset-driven Evaluation
%J Computer Science and Information Systems
%D 2026
%V 23
%N 1
%U http://geodesic.mathdoc.fr/item/CSIS_2026_23_1_a26/
%F CSIS_2026_23_1_a26