Fuzzy Sentiment Analysis for Improving German Learning in Corpus-Based Deep Learning Approaches

Guardado en:

Detalles Bibliográficos
Publicado en:	International Journal of Web-Based Learning and Teaching Technologies vol. 20, no. 1 (2025), p. 1-23
Autor principal:	Dong, Qi
Publicado:	IGI Global
Materias:	Students Tutoring Deep learning Emotional states Technology Educational technology Emotions Sentiment analysis Learning Motivation Corpus analysis Effectiveness Classifiers Emotional factors Language acquisition Feedback Corpus linguistics Fuzzy logic Intelligence Artificial intelligence User satisfaction Natural language processing Satisfaction Customization Literature Reviews Learning Motivation Long Term Memory Memory Student Motivation Language Processing Algorithms Grammar Language Usage Educational Resources Language Skills Distance Education Influence of Technology Intelligent Tutoring Systems Language Research Addition Learning Processes Learning Experience Native Language Native Speakers Data Analysis Educational Facilities Improvement
Acceso en línea:	Citation/Abstract Full Text - PDF
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Descripción
Resumen:	This study aims to explore how to optimize corpus-based deep learning methods by introducing fuzzy sentiment analysis technology to improve the effectiveness and interactivity of German learning. By building an intelligent tutoring system that can perceive the emotional state of German learners, the effectiveness and interactivity of learning can be improved. Experimental results show that the fuzzy sentiment classifier has significant advantages in language skill improvement, user satisfaction, learning motivation, and sustained engagement. Fuzzy sentiment analysis technology can capture and process learners' emotional states more delicately, provide personalized feedback and support, and identify individual learning patterns and preferences based on long-term accumulated data, thereby recommending customized learning paths.
ISSN:	1548-1093 1548-1107
DOI:	10.4018/IJWLTT.383940
Fuente:	Engineering Database