Music emotion recognition today is based on techniques that require high quality and large emotionally labeled sets of songs to train algorithms. Manual and professional annotations of songs are costly and hardly accomplished. There is a high need for datasets that are public, highly polarized, large in size and following popular emotion representation models. In this paper we present the steps we followed to create two such datasets using intelligence of last.fm community tags. In the first dataset, songs are categorized based on an emotion space of four clusters we adopted from literature observations. The second dataset discriminates between positive and negative songs only. We also observed that last.fm mood tags are biased towards positive emotions. This imbalance of tags was reflected in cluster sizes of the resulting datasets we obtained; they contain more positive songs than negative ones.

Music Mood Dataset Creation Based on Last.fm Tags / Cano, Erion; Morisio, Maurizio. - ELETTRONICO. - 7:(2017), pp. 15-26. (Intervento presentato al convegno Fourth International Conference on Artificial Intelligence and Applications (AIAP 2017) tenutosi a Vienna, Austria nel 27-28 May 2017) [10.5121/csit.2017.70603].

Music Mood Dataset Creation Based on Last.fm Tags

CANO, ERION;MORISIO, MAURIZIO
2017

Abstract

Music emotion recognition today is based on techniques that require high quality and large emotionally labeled sets of songs to train algorithms. Manual and professional annotations of songs are costly and hardly accomplished. There is a high need for datasets that are public, highly polarized, large in size and following popular emotion representation models. In this paper we present the steps we followed to create two such datasets using intelligence of last.fm community tags. In the first dataset, songs are categorized based on an emotion space of four clusters we adopted from literature observations. The second dataset discriminates between positive and negative songs only. We also observed that last.fm mood tags are biased towards positive emotions. This imbalance of tags was reflected in cluster sizes of the resulting datasets we obtained; they contain more positive songs than negative ones.
2017
978-1-921987-66-3
File in questo prodotto:
File Dimensione Formato  
ErionCanoMoodyLyrics2.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 553.49 kB
Formato Adobe PDF
553.49 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2669975
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo