Bisociative Music Discovery and Recommendation

Abstract

Abstract. Surprising a user with unexpected and fortunate recommendations is a key challenge for recommender systems. Motivated by the concept of bisociations, we propose ways to create an environment where such serendipitous recommendations become more likely. As application domain we focus on music recommendation using MusicGalaxy, an adaptive user-interface for exploring music collections. It leverages a nonlinear multi-focus distortion technique that adaptively highlights related music tracks in a projection-based collection visualization depending on the current region of interest. While originally developed to alleviate the impact of inevitable projection errors, it can also adapt according to user-preferences. We discuss how using this technique beyond its original purpose can create distortions of the visualization that facilitate bisociative music discovery.

Creative exploration using topic-based bisociative networks

“…Researchers have applied BisoNets to exploration of Biological and Financial Literature (Schmidt et al 2012) and Music Discovery (Stober et al 2012), with unstructured text documents being one of the most widely used (and most challenging) applications. These past text-based approaches work well when there are specific, technical terms embedded in documents that are shared between domains.…”

Applications and Evaluation: Overview

“…Finally, Stober et al [12] present an advanced user interface for music recommendation. Here, the concept of bisociation provides motivation for unexpected and fortunate (serendipitous) recommendations.…”