Predicting GEMS Based on PDA-Assessed Gestural Motion Data

Melanie Irrgang, Hauke Egermann, Esra Acar, Andreas Lommatzsch

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Music is often discussed to be perceived as emotional because it renders expressive movements into audible musical structures. Thus, a valid approach to measure musical emotion could be to assess movement stimulated by music. This study evaluated the discriminative power of mobile-device generated acceleration data produced by free movement during music listening experience for the prediction of different degrees of the Geneva Emotion Music Scales (GEMS-9). The variance of the perceived GEMS-states can be explained by the fitted models as follows: power (r2 = .36), sadness (r2 = .17), tenderness (r2 = .14), joy (r2 = .15), tension (r2 = .11), peacefulness (r2 = .08), nostalgia (r2 = .07), wonder (r2 = .07) and transcendence (r2 = .02). These findings will contribute to understand, how acceleration data can be used to integrate embodied music cognition into Music Recommender Systems.
Original languageUndefined/Unknown
Title of host publicationProceedings of the 11th International Symposium on Computer Music Multidisciplinary Research (CMMR) Music, Mind, and Embodiment
EditorsRichard Kronland-Martinet, Mitsuko Aramaki, Sølvi Ystad, Joel Eaton
PublisherInterdisciplinary Centre for Computer Music Research
Number of pages14
Publication statusPublished - 2015


  • embodiment,emotion,gems,music information retrieval,music recommender systems

Cite this