Content Aware Playlist Generation with Multi-Dimensional Similarity Measure

Music players and cloud solution for music recomme ndation and automatic playlist creation are becoming increasing ly more popular, as they intent to overcome the issue of the difficulty for users t o find fitting music, based on context, mood and impression. Much research on the topic has been conducted, which has recommended different approaches to overc me this problem. This paper suggests a system which uses a multi-dimensio nal vector space, based on the music’s key elements, as well as the mood expressed through them and the song lyrics, which allows for difference and similarity finding to automatically generate a contextually meaningful playlist.

[1]  B. Cooper.  Performing Rites: On the Value of Popular Music , 1998 .

[2]  I. Peretz,et al.  Exposure effects on music preference and recognition , 1998, Memory & cognition.

[3]  R. Thayer.  The biopsychology of mood and arousal , 1989 .

[4]  Sibylle Moser.  Media modes of poetic reception: Reading lyrics versus listening to songs , 2007 .

[5]  Jun Hu,et al.  Music Playlist Recommendation Based on User Heartbeat and Music Preference , 2009, 2009 International Conference on Computer Technology and Development.

[6]  Yasushi Kiyoki,et al.  Information Modelling and Knowledge Bases XXV , 2004 .

[8]  Lie Lu,et al.  Automatic mood detection and tracking of music audio signals , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[9]  Lillian Lee,et al.  Opinion Mining and Sentiment Analysis , 2008, Found. Trends Inf. Retr..

[10]  Xing Chen,et al.  A Semantic Associative Computation Method for Automatic Decorative-Multimedia Creation with 'Kansei' Information , 2009, APCCM.

[11]  Dan Yang,et al.  Disambiguating Music Emotion Using Software Agents , 2004, ISMIR.

[12]  Xing Chen,et al.  Contextual and Differential Computing for the Multi-Dimensional World Map with Context-Specific Spatial-Temporal and Semantic Axes , 2013, EJC.

[13]  Daniel J Levitin,et al.  The structure of musical preferences: a five-factor model. , 2011, Journal of personality and social psychology.

[14]  Amy Beth Warriner,et al.  Norms of valence, arousal, and dominance for 13,915 English lemmas , 2013, Behavior Research Methods.

[15]  Janyce Wiebe,et al.  Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis , 2005, HLT.

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

[17]  Bamshad Mobasher,et al.  The Role of Emotions in Context-aware Recommendation , 2013, Decisions@RecSys.

[18]  Lior Rokach,et al.  Best Usage Context Prediction for Music Tracks , 2010 .

[19]  Man-Kwan Shan,et al.  A personalized music filtering system based on melody style classification , 2002, 2002 IEEE International Conference on Data Mining, 2002. Proceedings..

[20]  Xiao Hu,et al.  Music and Mood: Where Theory and Reality Meet , 2010 .

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

[22]  Björn W. Schuller,et al.  Determination of Nonprototypical Valence and Arousal in Popular Music: Features and Performances , 2010, EURASIP J. Audio Speech Music. Process..

[23]  Kiyoaki Shirai,et al.  Machine Learning Approaches for Mood Classification of Songs toward Music Search Engine , 2009, 2009 International Conference on Knowledge and Systems Engineering.

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