Accès libre

Research on the optimisation of music education curriculum content and implementation path based on big data analysis

Menghan Li

Menghan Li

Department of Music, School of Arts and Communication, China University of Geosciences (Wuhan)Wuhan, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Li, Menghan
 et 
Li Zhang

Li Zhang

Department of Music, School of Arts and Communication, China University of Geosciences (Wuhan)Wuhan, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Zhang, Li
  
05 févr. 2025
Research on the optimisation of music education curriculum content and implementation path based on big data analysis's Cover Image
À propos de cet article
Article précédent
Article suivant
Citez
Télécharger la couverture
Publié en ligne: 05 févr. 2025
Reçu: 27 sept. 2024
Accepté: 06 janv. 2025
DOI: https://doi.org/10.2478/amns-2025-0067
Mots clés
© 2025 Menghan Li et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

Big data processing platform
Big data processing platform

Figure 2.

Data mining model diagram
Data mining model diagram

Figure 3.

HDFS Architecture
HDFS Architecture

Figure 4.

MapReduce calculation process
MapReduce calculation process

Figure 5.

Schematic diagram of random walk strategy
Schematic diagram of random walk strategy

Figure 6.

Student/course relationship
Student/course relationship

Figure 7.

Evaluation of the effectiveness of course content recommendation
Evaluation of the effectiveness of course content recommendation

Figure 8.

Text quantity distribution of individual students
Text quantity distribution of individual students

Figure 9.

Text length distribution of student behavior
Text length distribution of student behavior

Figure 10.

Model performance on data sets with different sparsity
Model performance on data sets with different sparsity

Results of recommended performance indicators for each model

Model Pre@20 Recall@20 NDCG@20 MRR AUC
MF 0.11521 0.10156 0.02516 0.01408 0.50423
HERec 0.14722 0.13489 0.05069 0.03023 0.62355
NGCF 0.18836 0.15266 0.58996 0.04815 0.65882
ACKRec 0.19156 0.16189 0.06251 0.05047 0.67321
MOOCIR 0.19554 0.16205 0.06322 0.06381 0.68011
HFCNqh 0.02131 0.18732 0.07182 0.06852 0.72342
HFCNqk 0.19983 0.17956 0.07134 0.06433 0.69834
HFCNqb 0.02015 0.18090 0.07560 0.06385 0.70705
Node2vec 0.02349 0.19849 0.08686 0.07472 0.75336
Improvement (%) 10.23% 5.96% 14.89% 9.05% 4.14%

Partitioning results based on learner interaction data

Data set Groups Number of users Number of courses Users-courses Density (%)
MOOC music course content recommended data set (0, 5] 25510 596 82694 0.61%
(5, 15] 4583 575 34566 1.55%
(15, 30] 284 432 4315 4.56%
(30, 100] 42 401 1675 11.05%
Langue:
Anglais
Périodicité:
1 fois par an
Sujets de la revue:
Sciences de la vie, Sciences de la vie, autres, Mathématiques, Mathématiques appliquées, Mathématiques générales, Physique, Physique, autres
RSS Feed de la revue