A Hybrid Recommender System for Improving Automatic Playlist Continuation

Although widely used, the majority of current music recommender systems still focus on recommendations' accuracy, user preferences and isolated item characteristics, without evaluating other important factors, like the joint item selections and the recommendation moment. However, when it comes...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on knowledge and data engineering 2021-05, Vol.33 (5), p.1819-1830
Main Authors: Gatzioura, Anna, Vinagre, Joao, Jorge, Alipio Mario, Sanchez-Marre, Miquel
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
automatic playlist continuation
beyond accuracy dimensions
case-based reasoning
Cognition
Coherence
Dirichlet problem
Hybrid recommender system
Hybrid systems
latent dirichlet allocation
Music
music recommender systems
Prediction algorithms
Recommender systems
Semantics
User experience
User requirements
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Although widely used, the majority of current music recommender systems still focus on recommendations' accuracy, user preferences and isolated item characteristics, without evaluating other important factors, like the joint item selections and the recommendation moment. However, when it comes to playlist recommendations, additional dimensions, as well as the notion of user experience and perception, should be taken into account to improve recommendations' quality. In this work, HybA, a hybrid recommender system for automatic playlist continuation, that combines Latent Dirichlet Allocation and Case-Based Reasoning, is proposed. This system aims to address "similar concepts" rather than similar users. More than generating a playlist based on user requirements, like automatic playlist generation methods, HybA identifies the semantic characteristics of a started playlist and reuses the most similar past ones, to recommend relevant playlist continuations. In addition, support to beyond accuracy dimensions, like increased coherence or diverse items' discovery, is provided. To overcome the semantic gap between music descriptions and user preferences, identify playlist structures and capture songs' similarity, a graph model is used. Experiments on real datasets have shown that the proposed algorithm is able to outperform other state of the art techniques, in terms of accuracy, while balancing between diversity and coherence.
ISSN:1041-4347
1558-2191
DOI:10.1109/TKDE.2019.2952099