Music Playlist Title Generation Using Artist Information

TL;DR

This paper proposes an artist-based encoder-decoder model for automatic music playlist title generation, improving relevance and diversity over track ID-based methods, and introduces a chronological data split for real-world applicability.

Contribution

It introduces an artist ID-based input method and a chronological data split approach, advancing playlist title generation for better relevance and handling new tracks.

Findings

Artist-based input improves title relevance and diversity.

Chronological data split enhances real-world applicability.

Model outperforms track ID-based methods in key metrics.

Abstract

Automatically generating or captioning music playlist titles given a set of tracks is of significant interest in music streaming services as customized playlists are widely used in personalized music recommendation, and well-composed text titles attract users and help their music discovery. We present an encoder-decoder model that generates a playlist title from a sequence of music tracks. While previous work takes track IDs as tokenized input for playlist title generation, we use artist IDs corresponding to the tracks to mitigate the issue from the long-tail distribution of tracks included in the playlist dataset. Also, we introduce a chronological data split method to deal with newly-released tracks in real-world scenarios. Comparing the track IDs and artist IDs as input sequences, we show that the artist-based approach significantly enhances the performance in terms of word overlap, semantic relevance, and diversity.