Music Mood Dataset Creation Based on Last.fm Tags

Music emotion recognition today is based on techniques that require high quality and large emotionally labeled sets of songs to train algorithms. Manual and professional annotations of songs are costly and hardly accomplished. There is a high need for datasets that are public, highly polarized, large in size and following popular emotion representation models. In this paper we present the steps we followed to create two such datasets using intelligence of last.fm community tags. In the first dataset, songs are categorized based on an emotion space of four clusters we adopted from literature observations. The second dataset discriminates between positive and negative songs only. We also observed that last.fm mood tags are biased towards positive emotions. This imbalance of tags was reflected in cluster sizes of the resulting datasets we obtained; they contain more positive songs than negative ones.

[1]  Maurizio Morisio,et al.  MoodyLyrics: A Sentiment Annotated Lyrics Dataset , 2017, ISMSI '17.

[2]  Mert Bay,et al.  Creating a Simplified Music Mood Classification Ground-Truth Set , 2007, ISMIR.

[3]  Jeffrey J. Scott,et al.  State of the Art Report: Music Emotion Recognition: A State of the Art Review , 2010, ISMIR.

[4]  J. Stephen Downie,et al.  Exploring Mood Metadata: Relationships with Genre, Artist and Usage Metadata , 2007, ISMIR.

[5]  D. Watson,et al.  On the Dimensional and Hierarchical Structure of Affect , 1999 .

[6]  Minho Kim,et al.  Lyrics-Based Emotion Classification Using Feature Selection by Partial Syntactic Analysis , 2011, 2011 IEEE 23rd International Conference on Tools with Artificial Intelligence.

[7]  Rui Pedro Paiva,et al.  Classification and Regression of Music Lyrics: Emotionally-Significant Features , 2016, KDIR.

[8]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[9]  M. Bradley,et al.  Affective Norms for English Words (ANEW): Instruction Manual and Affective Ratings , 1999 .

[10]  Brandon G. Morton,et al.  A Comparative Study of Collaborative vs. Traditional Musical Mood Annotation , 2011, ISMIR.

[11]  Menno van Zaanen,et al.  Automatic Mood Classification Using TF*IDF Based on Lyrics , 2010, ISMIR.

[12]  K. Hevner.  Experimental studies of the elements of expression in music , 1936 .

[13]  M. Bradley,et al.  Affective Normsfor English Words (ANEW): Stimuli, instruction manual and affective ratings (Tech Report C-1) , 1999 .

[14]  Nicola Orio,et al.  A professionally annotated and enriched multimodal data set on popular music , 2013, MMSys.

[15]  Yi-Hsuan Yang,et al.  Exploiting online music tags for music emotion classification , 2011, TOMCCAP.

[16]  Thierry Bertin-Mahieux,et al.  The Million Song Dataset , 2011, ISMIR.

[17]  Hui He,et al.  Language Feature Mining for Music Emotion Classification via Supervised Learning from Lyrics , 2008, ISICA.

[18]  J. Russell.  A circumplex model of affect. , 1980 .

[19]  Paul Lamere,et al.  Social Tags and Music Information Retrieval , 2008, International Society for Music Information Retrieval Conference.

[20]  J. Stephen Downie,et al.  When Lyrics Outperform Audio for Music Mood Classification: A Feature Analysis , 2010, ISMIR.

[21]  Ting Liu,et al.  Deep learning for sentiment analysis: successful approaches and future challenges , 2015, WIREs Data Mining Knowl. Discov..

[22]  Andreas F. Ehmann,et al.  Lyric Text Mining in Music Mood Classification , 2009, ISMIR.

[23]  J. Stephen Downie,et al.  Improving mood classification in music digital libraries by combining lyrics and audio , 2010, JCDL '10.

[24]  Xiao Hu,et al.  Generating ground truth for music mood classification using mechanical turk , 2012, JCDL '12.

[25]  Zhouyu Fu,et al.  A Survey of Audio-Based Music Classification and Annotation , 2011, IEEE Transactions on Multimedia.

[26]  Wolfgang Nejdl,et al.  Music Mood and Theme Classification - a Hybrid Approach , 2009, ISMIR.

[27]  Joan Serrà,et al.  Music Mood Representations from Social Tags , 2009, ISMIR.

[28]  Carlo Strapparava,et al.  Lyrics, Music, and Emotions , 2012, EMNLP.

[29]  Christopher Potts,et al.  Learning Word Vectors for Sentiment Analysis , 2011, ACL.

[30]  Gert R. G. Lanckriet,et al.  Semantic Annotation and Retrieval of Music and Sound Effects , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[31]  Thorsten Joachims,et al.  Playlist prediction via metric embedding , 2012, KDD.

[32]  Grigorios Tsoumakas,et al.  Multi-Label Classification of Music into Emotions , 2008, ISMIR.