Music Recommendation Algorithm Based on Multidimensional Time-Series Model Analysis

This paper proposes a personalized music recommendation method based on multidimensional time-series analysis, which can improve the effect of music recommendation by using user’s midterm behavior reasonably. This method uses the theme model to express each song as the probability of belonging to se...

Full description

Saved in:
Bibliographic Details
Main Author: Juanjuan Shi
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2021/5579086
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832568483723870208
author Juanjuan Shi
author_facet Juanjuan Shi
author_sort Juanjuan Shi
collection DOAJ
description This paper proposes a personalized music recommendation method based on multidimensional time-series analysis, which can improve the effect of music recommendation by using user’s midterm behavior reasonably. This method uses the theme model to express each song as the probability of belonging to several hidden themes, then models the user’s behavior as multidimensional time series, and analyzes the series so as to better predict the use of music users’ behavior preference and give reasonable recommendations. Then, a music recommendation method is proposed, which integrates the long-term, medium-term, and real-time behaviors of users and considers the dynamic adjustment of the influence weight of the three behaviors so as to further improve the effect of music recommendation by adopting the advanced long short time memory (LSTM) technology. Through the implementation of the prototype system, the feasibility of the proposed method is preliminarily verified.
format Article
id doaj-art-2d7a1c54bd2e4d70833b3cc7f7937ec9
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-2d7a1c54bd2e4d70833b3cc7f7937ec92025-02-03T00:58:59ZengWileyComplexity1076-27871099-05262021-01-01202110.1155/2021/55790865579086Music Recommendation Algorithm Based on Multidimensional Time-Series Model AnalysisJuanjuan Shi0ZhongShan Polytechnic, Zhongshan, Guangdong 528400, ChinaThis paper proposes a personalized music recommendation method based on multidimensional time-series analysis, which can improve the effect of music recommendation by using user’s midterm behavior reasonably. This method uses the theme model to express each song as the probability of belonging to several hidden themes, then models the user’s behavior as multidimensional time series, and analyzes the series so as to better predict the use of music users’ behavior preference and give reasonable recommendations. Then, a music recommendation method is proposed, which integrates the long-term, medium-term, and real-time behaviors of users and considers the dynamic adjustment of the influence weight of the three behaviors so as to further improve the effect of music recommendation by adopting the advanced long short time memory (LSTM) technology. Through the implementation of the prototype system, the feasibility of the proposed method is preliminarily verified.http://dx.doi.org/10.1155/2021/5579086
spellingShingle Juanjuan Shi
Music Recommendation Algorithm Based on Multidimensional Time-Series Model Analysis
Complexity
title Music Recommendation Algorithm Based on Multidimensional Time-Series Model Analysis
title_full Music Recommendation Algorithm Based on Multidimensional Time-Series Model Analysis
title_fullStr Music Recommendation Algorithm Based on Multidimensional Time-Series Model Analysis
title_full_unstemmed Music Recommendation Algorithm Based on Multidimensional Time-Series Model Analysis
title_short Music Recommendation Algorithm Based on Multidimensional Time-Series Model Analysis
title_sort music recommendation algorithm based on multidimensional time series model analysis
url http://dx.doi.org/10.1155/2021/5579086
work_keys_str_mv AT juanjuanshi musicrecommendationalgorithmbasedonmultidimensionaltimeseriesmodelanalysis