Emotionally-relevant features for classification and regression of music lyrics

Ver registo simples
dc.contributor.authorMalheiro, Ricardo
dc.contributor.authorPanda, Renato
dc.contributor.authorGomes, Paulo
dc.contributor.authorPaiva, Rui Pedro
dc.date.accessioned2017-10-13T14:43:10Z
dc.date.available2017-10-13T14:43:10Z
dc.date.issued2016-08-08
dc.description.abstractThis research addresses the role of lyrics in the music emotion recognition process. Our approach is based on several state of the art features complemented by novel stylistic, structural and semantic features. To evaluate our approach, we created a ground truth dataset containing 180 song lyrics, according to Russell’s emotion model. We conduct four types of experiments: regression and classification by quadrant, arousal and valence categories. Comparing to the state of the art features (ngrams - baseline), adding other features, including novel features, improved the F-measure from 69.9%, 82.7% and 85.6% to 80.1%, 88.3% and 90%, respectively for the three classification experiments. To study the relation between features and emotions (quadrants) we performed experiments to identify the best features that allow to describe and discriminate each quadrant. To further validate these experiments, we built a validation set comprising 771 lyrics extracted from the AllMusic platform, having achieved 73.6% F-measure in the classification by quadrants. We also conducted experiments to identify interpretable rules that show the relation between features and emotions and the relation among features. Regarding regression, results show that, comparing to similar studies for audio, we achieve a similar performance for arousal and a much better performance for valence.pt_PT
dc.identifier.other10.1109/TAFFC.2016.2598569
dc.identifier.urihttp://repositorio.ismt.pt/handle/123456789/720
dc.language.isoenpt_PT
dc.publisherIEEE TRANSACTIONS ON JOURNAL AFFECTIVE COMPUTING, MANUSCRIPT IDpt_PT
dc.subjectrecognition of group emotionpt_PT
dc.subjectaffective computingpt_PT
dc.subjectaffective computing applicationspt_PT
dc.subjectmusic retrieval and generationpt_PT
dc.subjectnatural language processingpt_PT
dc.titleEmotionally-relevant features for classification and regression of music lyricspt_PT
dc.typeArticlept_PT
Ficheiros
Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Transactions on Affective Computing Journal - TAC2016.pdf
Tamanho:
1.28 MB
Formato:
Adobe Portable Document Format
Descrição:
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura
Nome:
license.txt
Tamanho:
1.71 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir
Coleções
Publicações Científicas C e T