Associated with the Linz Institute of Technology and the Institute of Computational Perception @ JKU Linz, Austria

Emotion-calibrated Music Recommendation

emotion_calibration Teaser

Abstract

Emotions constitute an important aspect when listening to music. This has motivated the development of high-quality emotion characterizations of music tracks that can be used for music recommender systems (MRS) that rely on emotion information. Although previous studies evaluate the accuracy of emotion-informed MRS, surprisingly there are no studies that analyze whether music recommendations reflect the distribution of emotions over music catalogs and, more importantly, over users' past listening history. In this work we show that MRS tend to over-represent some emotions in the recommendation lists, compared with both the music catalog and the users' listening history. With this insight, we propose the use of emotion calibration in MRS and show that this has no substantial impact on recommendation accuracy.


Citation

Marta Moscati, Emra Gurung, Shah Nawaz, swain, Markus Schedl
Emotion-calibrated Music Recommendation
Proceedings of the 4th Music Recommender Systems Workshop (MuRS) co-located with the 20th ACM Conference on Recommender Systems (RecSys 2026), Minneapolis, Minnesota, US., 2026.

BibTeX

@proceedings{Moscati2026emotion_calibration,
    title = {Emotion-calibrated Music Recommendation},
    author = {Moscati, Marta and Emra Gurung and Nawaz, Shah and swain and Schedl, Markus},
    booktitle = {Proceedings of the 4th Music Recommender Systems Workshop (MuRS) co-located with the 20th ACM Conference on Recommender Systems (RecSys 2026), Minneapolis, Minnesota, US.},
    editor = {Ferraro, Andrés and Porcaro, Lorenzo and Moscati, Marta and Bauer, Christine},
    publisher = {CEUR-WS.org},
    year = {2026}
}