Open AccessProceedings Article
Lyric text mining in music mood classification
Xiao Hu,J. Stephen Downie,Andreas F. Ehmann +2 more
- pp 411-416
TLDR
Findings show patterns at odds with findings in previous studies: audio features do not always outperform lyrics features, and combining lyrics and audio features can improve performance in many mood categories, but not all of them.Abstract:
This research examines the role lyric text can play in improving audio music mood classification. A new method is proposed to build a large ground truth set of 5,585 songs and 18 mood categories based on social tags so as to reflect a realistic, user-centered perspective. A relatively complete set of lyric features and representation models were investigated. The best performing lyric feature set was also compared to a leading audio-based system. In combining lyric and audio sources, hybrid feature sets built with three different feature selection methods were also examined. The results show patterns at odds with findings in previous studies: audio features do not always outperform lyrics features, and combining lyrics and audio features can improve performance in many mood categories, but not all of them.read more
Citations
More filters
Music emotion recognition: A state of the art review
Youngmoo E. Kim,Erik M. Schmidt,Raymond Migneco,Brandon G. Morton,Patrick Richardson,Jeffrey J. Scott,Jacquelin A. Speck,Douglas Turnbull +7 more
TL;DR: A survey of the state of the art in automatic emotion recognition in music can be found in this article, where the authors explore a wide range of research in music emotion recognition, particularly focusing on methods that use contextual text information (e.g., websites, tags, and lyrics) and content-based approaches, as well as systems combining multiple feature domains.
Journal ArticleDOI
Machine Recognition of Music Emotion: A Review
Yi-Hsuan Yang,Homer H. Chen +1 more
TL;DR: This article provides a comprehensive review of the methods that have been proposed for music emotion recognition and concludes with suggestions for further research.
Journal ArticleDOI
A functional MRI study of happy and sad emotions in music with and without lyrics
Elvira Brattico,Elvira Brattico,Vinoo Alluri,Brigitte Bogert,Brigitte Bogert,Thomas Jacobsen,Nuutti Vartiainen,Sirke Nieminen,Sirke Nieminen,Mari Tervaniemi,Mari Tervaniemi +10 more
TL;DR: The role of acoustic cues for the experience of happiness in music and to the importance of lyrics for sad musical emotions are pointed to.
Journal ArticleDOI
A Unified Framework for Providing Recommendations in Social Tagging Systems Based on Ternary Semantic Analysis
TL;DR: The approach develops a unified framework to model the three types of entities that exist in a social tagging system: users, items, and tags using a 3-order tensor, on which multiway latent semantic analysis and dimensionality reduction is performed.
Journal ArticleDOI
A survey of music similarity and recommendation from music context data
Peter Knees,Markus Schedl +1 more
TL;DR: An overview of methods for music similarity estimation and music recommendation based on music context data is given and the characteristics of the presented context-based measures are elaborates and discusses their strengths as well as their weaknesses.
References
More filters
Journal ArticleDOI
LIBSVM: A library for support vector machines
Chih-Chung Chang,Chih-Jen Lin +1 more
TL;DR: Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
Book
Opinion Mining and Sentiment Analysis
Bo Pang,Lillian Lee +1 more
TL;DR: This survey covers techniques and approaches that promise to directly enable opinion-oriented information-seeking systems and focuses on methods that seek to address the new challenges raised by sentiment-aware applications, as compared to those that are already present in more traditional fact-based analysis.
Proceedings Article
WordNet Affect: an Affective Extension of WordNet
TL;DR: A linguistic resource for the lexical representation of affective knowledge was developed starting from WORDNET, through a selection and tagging of a subset of synsets representing the affective.
Book ChapterDOI
Combining SVMs with Various Feature Selection Strategies
Yi-Wei Chen,Chih-Jen Lin +1 more
TL;DR: This article investigates the performance of combining support vector machines (SVM) and various feature selection strategies, some are filter-type approaches: general feature selection methods independent of SVM, and some are wrapper-type methods: modifications of S VM which can be used to select features.