Graph-RAT: Combining data sources in music recommendation systems

The complexity of music recommendation systems has increased rapidly in recent years, drawing upon different sources of information: content analysis, web-mining, social tagging, etc. Unfortunately, the tools to scientifically evaluate such integrated systems are not readily available; nor are the base algorithms available. This article describes Graph-RAT (Graph-based Relational Analysis Toolkit), an open source toolkit that provides a framework for developing and evaluating novel hybrid systems. While this toolkit is designed for music recommendation, it has applications outside its discipline as well. An experiment—indicative of the sort of procedure that can be configured using the toolkit—is provided to illustrate its usefulness.

[1]  Fabio Vignoli,et al.  Virtual Communities for Creating Shared Music Channels , 2007, ISMIR.

[2]  Masataka Goto,et al.  Hybrid Collaborative and Content-based Music Recommendation Using Probabilistic Model with Latent User Preferences , 2006, ISMIR.

[3]  Masataka Goto,et al.  MusicSun: A New Approach to Artist Recommendation , 2007, ISMIR.

[4]  Berry Eggen,et al.  Realization and User Evaluation of an Automatic Playlist Generator , 2003, ISMIR.

[5]  Perfecto Herrera,et al.  Getting music recommendations and filtering newsfeeds from FOAF descriptions , 2005 .

[6]  David Jensen,et al.  Unique Challenges of Managing Inductive Knowledge , 1997 .

[7]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[8]  Arbee L. P. Chen,et al.  A music recommendation system based on music data grouping and user interests , 2001, CIKM '01.

[9]  Masataka Goto,et al.  Improving Efficiency and Scalability of Model-Based Music Recommender System Based on Incremental Training , 2007, ISMIR.

[10]  Òscar Celma,et al.  Good Vibrations: Music Discovery through Personal Musical Concepts , 2006, ISMIR.

[11]  Steffen Pauws,et al.  Fast Generation of Optimal Music Playlists using Local Search , 2006, ISMIR.

[12]  Fabio Vignoli,et al.  Ensemble Learning for Hybrid Music Recommendation , 2007, ISMIR.

[13]  Tim Pohle,et al.  Dynamic Playlist Generation Based on Skipping Behavior , 2005, ISMIR.

[14]  J. Stephen Downie,et al.  The International Music Information Retrieval Systems Evaluation Laboratory: Governance, Access and Security , 2004, ISMIR.

[15]  Elias Pampalk,et al.  An Implementation of a Simple Playlist Generator Based on Audio Similarity Measures and User Feedback , 2006, ISMIR.

[16]  Vladimir Batagelj,et al.  Centrality in Social Networks , 1993 .

[17]  M E J Newman,et al.  Finding and evaluating community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[18]  Carl D. Meyer,et al.  Deeper Inside PageRank , 2004, Internet Math..

[19]  Kristian J. Hammond,et al.  Flytrap: intelligent group music recommendation , 2002, IUI '02.

[20]  Beth Logan,et al.  Music Recommendation from Song Sets , 2004, ISMIR.