Eliminating Cold-Start Problem of Music Recommendation through SOM Based Sampling

Ning Han Liu; Cheng Yu Chiang; Hsiang Ming Hsu

doi:10.4028/www.scientific.net/AMM.278-280.1119

Paper Titles

Simulation of Four-Stage Doherty Power Amplifier Structure
p.1095

A New Period Detecting Method for Periodic Signal Based on Singular Value Decomposition
p.1101

Coherent Demodulation of the Mud Pressure DPSK Signal and Analysis of Noise Impact on the Signal Demodulation
p.1107

Design and Implementation of Trigger-Based-on Document Data Acquisition Method
p.1114

Eliminating Cold-Start Problem of Music Recommendation through SOM Based Sampling
p.1119

Research of Enhanced Speech Signal Based on MATLAB Simulation Platform
p.1124

Based on Machine Vision of Smart Meter Recognition and Accurate Positioning Technology Research
p.1129

Decomposition with LMD of Mechanical Fault Signals Based on LabVIEW
p.1133

Design and Realization of Universal Radar Signal Processing Software
p.1137

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 278-280Eliminating Cold-Start Problem of Music...

Eliminating Cold-Start Problem of Music Recommendation through SOM Based Sampling

Abstract:

Recommendation systems have a prevalent cold-start problem. The problem is occurred might due to new users or new items (music) are added into the system. In this paper, the meaning of the cold-start is narrowed to that the systems do not understand the new user’s preferences. Therefore, systems can not recommend the music to users. Although many recommendation systems have a solution to reduce the cold-start, e.g., general systems utilize random to select songs. The systems random select some music works to user so that systems will know the user’s preferences after they rated the music works. However, systems may cost much time to collect the necessary information when the new user is interesting in some special types of music. Therefore, if systems select various type of music initially, the user’s preferences will be extracted more quickly. That is the cold-start problem can be reduced when the types of initial recommended music are various. In our approach, we utilize SOM to select some music from clusters. According to experiment, SOM selects type of music more average than k-means and random selection. Therefore, SOM can improve the cold-start problem and increase the precision of recommendation results.

You might also be interested in these eBooks

Advances in Mechatronics and Control Engineering

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 278-280)

Pages:

1119-1123

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.278-280.1119

Citation:

Cite this paper

Online since:

January 2013

Authors:

Ning Han Liu, Cheng Yu Chiang, Hsiang Ming Hsu

Keywords:

Clustering Algorithm, Cold-Start Problem, Music Recommendation, SOM

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Pandora Internet Radio and Music Genome Project on http://www.pandora.com.

Google Scholar

[2] N.H. Liu, S.W. Lai, C.Y. Chen and S.J. Hsieh, in: Adaptive Music Recommendation Based on User Behavior in Time Slot, in: International Journal of Computer Science and Network Security, Vol. 9-2(2009)

Google Scholar

[3] D. Eck, P. Lamere, T. Bertin-Mahieux and S. Green, in: Automatic Generation of Social Tags for Music Recommendation, in: Twenty-First Annual Conference on Neural Information Processing Systems, NIPS (2007)

Google Scholar

[4] J. Han and M. Kamber, in: Data Mining Concepts and Techniques, Morgan Kaufmann. (2001)

Google Scholar

[5] N.H. Liu, S.J. Shieh and C.F. Tsai, in: An Intelligent Music Playlist Generator based on the Time Parameter with Artificial Neural Networks, in: Expert systems with applications. Vol. 37-4 (2010), pp.2815-2825

DOI: 10.1016/j.eswa.2009.09.009

Google Scholar