Generating Interesting Song-to-Song Segues With Dave

TL;DR

This paper presents Dave, a novel algorithm for generating interesting song-to-song segues based on a scoring function for interestingness, demonstrating comparable or better quality than curated sources and aligning with human perceptions.

Contribution

The paper introduces a domain-independent algorithm for item-to-item textual connections, with a specific implementation for music, and a new scoring function for interestingness.

Findings

Dave generates 1553 types of segues categorized as informative or funny.

Dave's segues match or surpass curated sources in quality.

The scoring function correlates positively with human perceptions.

Abstract

We introduce a novel domain-independent algorithm for generating interesting item-to-item textual connections, or segues. Pivotal to our contribution is the introduction of a scoring function for segues, based on their "interestingness". We provide an implementation of our algorithm in the music domain. We refer to our implementation as Dave. Dave is able to generate 1553 different types of segues, that can be broadly categorized as either informative or funny. We evaluate Dave by comparing it against a curated source of song-to-song segues, called The Chain. In the case of informative segues, we find that Dave can produce segues of the same quality, if not better, than those to be found in The Chain. And, we report positive correlation between the values produced by our scoring function and human perceptions of segue quality. The results highlight the validity of our method, and open future directions in the application of segues to recommender systems research.