Keyword-Based Approach for Lyrics Emotion Variation Detection

Miniatura indisponível
Data
2016-01
Autores
Malheiro, Ricardo
Oliveira, Hugo Gonçalo
Gomes, Paulo
Paiva, Rui Pedro
Título da revista
ISSN da revista
Título do Volume
Editora
8th International Conference on Knowledge Discovery and Information Retrieval
Resumo
This research addresses the role of the lyrics in the context of music emotion variation detection. To accomplish this task we create a system to detect the predominant emotion expressed by each sentence (verse) of the lyrics. The system employs Russell’s emotion model and contains 4 sets of emotions associated to each quadrant. To detect the predominant emotion in each verse, we propose a novel keyword-based approach, which receives a sentence (verse) and classifies it in the appropriate quadrant. To tune the system parameters, we created a 129-sentence training dataset from 68 songs. To validate our system, we created a separate ground-truth containing 239 sentences (verses) from 44 songs annotated manually with an average of 7 annotations per sentence. The system attains 67.4% F-Measure score.
Descrição
Palavras-chave
Recuperação de informação musical - Music information retrieval, Reconhecimento emocional de letras de músicas - Lyrics music emotion recognition, Deteção de variação emocional com as letras das músicas - Lyrics music emotion variation detection, Abordagem baseada em palavras-chave - Keyword based approach
Citação
Malheiro, R, Oliveira H. G., Gomes, P. & Paiva, R. P. (2016). Keyword-Based Approach for Lyrics Emotion Variation Detection. 8th International Conference on Knowledge Discovery and Information Retrieval. DOI: 10.5220/0006037300330044