• Media type: Conference Proceedings; E-Article
  • Title: Toward a Musical Sentiment (MuSe) Dataset for Affective Distant Hearing
  • Contributor: Akiki, Christopher [Author]; Burghardt, Manuel [Author]
  • Published: Aachen: CEUR-WS.org, [2024]
  • Published in: Proceedings of the Workshop on Computational Humanities Research (CHR 2020) ; 2723, Seite 225-235
  • Language: English
  • Keywords: music emotion recognition ; music information retrieval ; music sentiment
  • Origination:
  • Footnote:
  • Description: In this short paper we present work in progress that tries to leverage crowdsourced music metadataand crowdsourced affective word norms to create a comprehensive dataset of music emotions, whichcan be used for sentiment analyses in the music domain. We combine a mixture of different datasources to create a new dataset of 90,408 songs with their associated embeddings in Russell’s modelof affect, with the dimensions valence, dominance and arousal. In addition, we provide a Spotify IDfor the songs, which can be used to add more metadata to the dataset via the Spotify API.
  • Access State: Open Access
  • Rights information: Attribution (CC BY)