Classification and Regression of Music Lyrics: Emotionally-Significant Features

Malheiro, Ricardo; Panda, Renato; Gomes, Paulo J. S.; Paiva, Rui Pedro

doi:10.5220/0006037400450055

Cited by 9 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the fact that authors warn about problems which can diminish annotations qualities, such as spamming, they conclude that MTurk represents a valid approach option. In [26] a lyrics dataset based on Valence-Arousal model of Russell [35] is created employing (AMG) tags. Likewise [13,31] and the work we present, Affective Norms for English Words (ANEW) [9] is used as a lexical resource.…”

Section: Related Workmentioning

confidence: 99%

“…Were "pleasure" represents positive versus negative emotions. We choose ANEW as seed lexicon because it is a) an established dictionary in the literature; b) suitable for large-scale texts; c) already attested to estimate and add valence scores for musical lyrics [13,26]; and because d) it is the seed lexicon exploited by the authors of the sentiment epidemic spreading algorithm. Pos(s) and Neg(s)) related to how objective, positive, and negative is, respectively.…”

Section: Lexical Resourcesmentioning

confidence: 99%

See 1 more Smart Citation

The italian music superdiversity

Pollacci

Guidotti

Rossetti

et al. 2018

Multimed Tools Appl

View full text Add to dashboard Cite

Globalization can lead to a growing standardization of musical contents. Using a cross-service multi-level dataset we investigate the actual Italian music scene. The investigation highlights the musical Italian superdiversity both individually analyzing the geographical and lexical dimensions and combining them. Using different kinds of features over the geographical dimension leads to two similar, comparable and coherent results, confirming the strong and essential correlation between melodies and lyrics. The profiles identified are markedly distinct one from another with respect to sentiment, lexicon, and melodic features. Through a novel application of a sentiment spreading algorithm and songs' melodic features, we are able to highlight discriminant characteristics that violate the standard regional political boundaries, reconfiguring them following the actual musical communicative practices.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Lexical Resourcesmentioning

confidence: 99%

The italian music superdiversity

Pollacci

Guidotti

Rossetti

et al. 2018

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…They make use of this dataset in [39] to evaluate the audio-text classifier they construct. A similar work is found in [40] where they use AMG tags to create a dataset of lyrics based on valencearousal model of Russell. Tags are first cleared and categorized in one of the 4 quadrants of the model using valence and arousal norms of ANEW [20].…”

Section: Music Tags From Community Usersmentioning

confidence: 99%

Crowdsourcing Emotions in Music Domain

Çano¹,

Morisio²

2017

IJAIA

View full text Add to dashboard Cite

show abstract

“…AllMusic Mood labels have also been used in [21] following a similar approach as taken in our paper but on a much smaller scale and a custom dataset. Outside the context of this paper AllMusic tags have been used in [22] to create a dataset of lyrics based on Valence-Arousal model.…”

Section: Introductionmentioning

confidence: 99%

Multi-Task Music Representation Learning from Multi-Label Embeddings

Strobel

Knees

2019

2019 International Conference on Content-Based Multimedia Indexing (CBMI)

View full text Add to dashboard Cite

This paper presents a novel approach to music representation learning. Triplet loss based networks have become popular for representation learning in various multimedia retrieval domains. Yet, one of the most crucial parts of this approach is the appropriate selection of triplets, which is indispensable, considering that the number of possible triplets grows cubically. We present an approach to harness multitag annotations for triplet selection, by using Latent Semantic Indexing to project the tags onto a high-dimensional space. From this we estimate tag-relatedness to select hard triplets. The approach is evaluated in a multi-task scenario for which we introduce four large multi-tag annotations for the Million Song Dataset for the music properties genres, styles, moods, and themes.

show abstract

Classification and Regression of Music Lyrics: Emotionally-Significant Features

Cited by 9 publications

References 14 publications

The italian music superdiversity

The italian music superdiversity

Crowdsourcing Emotions in Music Domain

Multi-Task Music Representation Learning from Multi-Label Embeddings

Contact Info

Product

Resources

About