Cargando…

Extraction of PE Online Teaching Resources With Positive Psychology Based on Advanced Intelligence Algorithm

Physical education (PE) teaching resources occupy a very important position in the teaching of PE theory. Especially in the context of the Internet era, how to effectively extract PE teaching resources from the Internet is very important for PE teachers. However, the quality of PE teaching resources...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Wei, Hu, Juan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9309176/
https://www.ncbi.nlm.nih.gov/pubmed/35899016
http://dx.doi.org/10.3389/fpsyg.2022.948721
Descripción
Sumario:Physical education (PE) teaching resources occupy a very important position in the teaching of PE theory. Especially in the context of the Internet era, how to effectively extract PE teaching resources from the Internet is very important for PE teachers. However, the quality of PE teaching resources on the Internet is uneven, if not correctly identified, it will bring harm to students’ values. Therefore, it is very necessary to correctly identify the teaching resources of positive psychology. In the era of artificial intelligence, advanced intelligent algorithms provide a solution for the realization of this purpose. In this study, a text sentiment analysis model multi-layer-attention convolutional neural network (ACNN)-CNN based on hierarchical CNN is proposed, which combines the advantages of convolutional neural networks and the attention mechanism. In multi-layer-ACNN-CNN, position encoding information is added to the embedding layer to improve the accuracy of text sentiment classification. In order to verify the performance of the model, online PE teaching resources are extracted by a crawler system and the proposed model is used to classify the positive psychology of the teaching resources. By comparison, the proposed model obtained a better positive psychology classification effect in the experiment, which verifies that the model can extract text features more accurately, and is more suitable for emotion classification of long texts.