Multi-label classification of music by emotion
TL;DR: This work focuses on multi-label classification approaches, where a piece of music may simultaneously belong to more than one class, and shows that multi- label modeling is successful and provides interesting insights into the predictive quality of the algorithms and features.
read more
Abstract: This work studies the task of automatic emotion detection in music. Music may evoke more than one different emotion at the same time. Single-label classification and regression cannot model this multiplicity. Therefore, this work focuses on multi-label classification approaches, where a piece of music may simultaneously belong to more than one class. Seven algorithms are experimentally compared for this task. Furthermore, the predictive power of several audio features is evaluated using a new multi-label feature selection method. Experiments are conducted on a set of 593 songs with six clusters of emotions based on the Tellegen-Watson-Clark model of affect. Results show that multi-label modeling is successful and provide interesting insights into the predictive quality of the algorithms and features.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Best-Laid Schemes: A Psychology of Emotions.
Elaine Wethington,Keith Oatley +1 more
TL;DR: In this article, the structure of emotions is discussed and an intuitive and empirical approach to understand it is proposed, together with a discussion of mutual plans and social emotions in fictional narratives.
751
Machine learning approach to auto-tagging online content for content marketing efficiency: A comparative analysis between methods and content type
Joni Salminen,Joni Salminen,Vignesh Yoganathan,Juan Corporan,Bernard J. Jansen,Soon-Gyo Jung +5 more
TL;DR: This work compares three state-of-the-art ML techniques for multilabel classification - Random Forest, K-Nearest Neighbor, and Neural Network - to automatically tag and classify online news articles and suggests that organisations may optimise ML to auto-tag content across various platforms, opening avenues for aggregated analyses of content performance.
89
Partial Multi-Label Learning with Noisy Label Identification.
Ming-Kun Xie,Sheng-Jun Huang +1 more
TL;DR: In this article, Li et al. proposed a multi-label learning approach to simultaneously recover the ground-truth information and identify the noisy labels in a unified framework with trace norm and l1 norm regularizers.
88
Feature construction and smote-based imbalance handling for multi-label learning
Nitin Mishra,Pramod K. Singh +1 more
TL;DR: The experimental results demonstrate the effectiveness of the proposed FCSMI method compared to the prevailing state-of-the-art multi-label sampling methods.
60
Land Classification Using Remotely Sensed Data: Going Multilabel
TL;DR: Experimental results suggest that the proposed framework can achieve excellent prediction accuracy, even from a limited number of diverse training examples, surpassing state-of-the-art spectral unmixing methods.
51
References
Multimodal Music Mood Classification Using Audio and Lyrics
C. Laurier,Jens Grivolla,Perfecto Herrera +2 more
- 11 Dec 2008
TL;DR: It is demonstrated that lyrics and audio information are complementary, and can be combined to improve a classification system, and integrating this in a multimodal system allows an improvement in the overall performance.
Sound Sentiment: An Essay on the Musical Emotions by Peter Kivy
Stephen Davies,Peter Kivy +1 more
TL;DR: Kivy as discussed by the authors argued that music possesses expressive properties, not as powers to arouse emotions in us but, rather, as perceived qualities of the music itself, and the Corded Shell: Reflections on Musical Expression was published in 1980 and now out of print.
170
•Proceedings Article
Disambiguating Music Emotion Using Software Agents.
Dan Yang,Won-Sook Lee +1 more
- 01 Jan 2004
TL;DR: Emo is a music annotation prototype that combines inputs from both human and software agents to better study human listening, and a functional theory of human emotion provides the basis for introducing necessary bias into the machine learning agents.
•Proceedings Article
Exploring Mood Metadata: Relationships with Genre, Artist and Usage Metadata.
Xiao Hu,J. Stephen Downie +1 more
- 01 Jan 2007
TL;DR: The relationships that mood has with genre, artist and usage metadata are explored and a cluster-based approach is recommended that overcomes specific term-related problems by creating a relatively small set of data-derived “mood spaces” that could form the ground-truth for a proposed MIREX “Automated Mood Classification” task.
Toward Multi-modal Music Emotion Classification
Yi-Hsuan Yang,Yu-Ching Lin,Heng-Tze Cheng,I-Bin Liao,Yeh-Chin Ho,Homer H. Chen +5 more
- 09 Dec 2008
TL;DR: By exploiting both the audio features and the lyrics of a song, the proposed approach improves the 4-class emotion classification accuracy from 46.6% to 57.1% and shows that the incorporation of lyrics significantly enhances the classification accuracy of valence.
97