Saved in:
Bibliographic Details
Main Authors: Choudhary, Yash, Rao, Preeti, Bhattacharyya, Pushpak
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.05508
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915656398536704
author Choudhary, Yash
Rao, Preeti
Bhattacharyya, Pushpak
author_facet Choudhary, Yash
Rao, Preeti
Bhattacharyya, Pushpak
contents Accurately predicting music popularity is a critical challenge in the music industry, offering benefits to artists, producers, and streaming platforms. Prior research has largely focused on audio features, social metadata, or model architectures. This work addresses the under-explored role of lyrics in predicting popularity. We present an automated pipeline that uses LLM to extract high-dimensional lyric embeddings, capturing semantic, syntactic, and sequential information. These features are integrated into HitMusicLyricNet, a multimodal architecture that combines audio, lyrics, and social metadata for popularity score prediction in the range 0-100. Our method outperforms existing baselines on the SpotGenTrack dataset, which contains over 100,000 tracks, achieving 9% and 20% improvements in MAE and MSE, respectively. Ablation confirms that gains arise from our LLM-driven lyrics feature pipeline (LyricsAENet), underscoring the value of dense lyric representations.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05508
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Lyrics Matter: Exploiting the Power of Learnt Representations for Music Popularity Prediction
Choudhary, Yash
Rao, Preeti
Bhattacharyya, Pushpak
Sound
Artificial Intelligence
Machine Learning
Accurately predicting music popularity is a critical challenge in the music industry, offering benefits to artists, producers, and streaming platforms. Prior research has largely focused on audio features, social metadata, or model architectures. This work addresses the under-explored role of lyrics in predicting popularity. We present an automated pipeline that uses LLM to extract high-dimensional lyric embeddings, capturing semantic, syntactic, and sequential information. These features are integrated into HitMusicLyricNet, a multimodal architecture that combines audio, lyrics, and social metadata for popularity score prediction in the range 0-100. Our method outperforms existing baselines on the SpotGenTrack dataset, which contains over 100,000 tracks, achieving 9% and 20% improvements in MAE and MSE, respectively. Ablation confirms that gains arise from our LLM-driven lyrics feature pipeline (LyricsAENet), underscoring the value of dense lyric representations.
title Lyrics Matter: Exploiting the Power of Learnt Representations for Music Popularity Prediction
topic Sound
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2512.05508