Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.13087/2075
Title: Alleviating the cold-start playlist continuation in music recommendation using latent semantic indexing
Authors: Yürekli, Ali
Kaleli, Cihan
Bilge, Alper
Keywords: Music recommender systems
Automatic playlist continuation
Cold-start problem
Latent semantic indexing
Ad hoc retrieval
Issue Date: 2021
Publisher: Springer
Abstract: The cold-start problem is a grand challenge in music recommender systems aiming to provide users with a better and continuous music listening experience. When a new user creates a playlist, the recommender system remains in a cold-start state until enough information is collected to identify the user's musical taste. In such cases, playlist metadata, such as title or description, have been successfully employed to create intent recommendation models. In this paper, we propose a multi-stage retrieval system utilizing user-generated titles to alleviate the cold-start problem in automatic playlist continuation. Initially, playlists are clustered to form a music documents collection. Then, the system applies latent semantic indexing to the collection to discover hidden patterns between tracks and playlist titles. For similarity calculation, singular value decomposition is performed on a track-cluster matrix. When the system is given a new playlist as a cold-start instance, it first retrieves neighboring clusters and then produces a ranked list of recommendations by weighting candidate tracks in these clusters. We scrutinize the performance of the proposed system on a large, real-world music playlists dataset supplied by the Spotify platform. Our empirical results show that the proposed system outperforms the state-of-the-art approaches and improves recommendation accuracy significantly in three primary evaluation metrics.
URI: https://doi.org/10.1007/s13735-021-00214-5
https://hdl.handle.net/20.500.13087/2075
ISSN: 2192-6611
2192-662X
Appears in Collections:İnşaat Mühendisliği Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu

Show full item record

CORE Recommender

Page view(s)

54
checked on Oct 3, 2022

Google ScholarTM

Check

Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.