<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The application of deep learning is becoming a research hotspot in education, especially in student sentiment analysis and classroom feedback prediction. Accurate sentiment analysis can help teachers understand their students’ learning status and improve their teaching effectiveness. In this study, we explored students’ emotional changes in different teaching environments through face detection technology and facial expression recognition. We predicted their feedback on classroom content, which optimized the teaching methods and enhanced students’ learning experience. The research methodology includes using the MTCNN face detection algorithm to locate students’ faces and analyzing facial expressions to recognize their emotional states through an improved deep learning model. In this study, the method was able to identify primary emotional states of students, including happiness, sadness, and surprise, with an accuracy of 85%. After analyzing the link between students’ emotions and classroom engagement, the study discovered that students’ positive emotional states were positively associated with high levels of classroom engagement. Student sentiment analysis is used to propose a classroom feedback prediction model that can predict student feedback on classroom content with 72% accuracy in this study. This paper utilizes deep learning to analyze student sentiment and predict classroom feedback, which improves teaching effectiveness and enhances students’ learning experience.</p>
</abstract>

The application of deep learning is becoming a research hotspot in education, especially in student sentiment analysis and classroom feedback prediction. Accurate sentiment analysis can help teachers understand their students’ learning status and improve their teaching effectiveness. In this study, we explored students’ emotional changes in different teaching environments through face detection technology and facial expression recognition. We predicted their feedback on classroom content, which optimized the teaching methods and enhanced students’ learning experience. The research methodology includes using the MTCNN face detection algorithm to locate students’ faces and analyzing facial expressions to recognize their emotional states through an improved deep learning model. In this study, the method was able to identify primary emotional states of students, including happiness, sadness, and surprise, with an accuracy of 85%. After analyzing the link between students’ emotions and classroom engagement, the study discovered that students’ positive emotional states were positively associated with high levels of classroom engagement. Student sentiment analysis is used to propose a classroom feedback prediction model that can predict student feedback on classroom content with 72% accuracy in this study. This paper utilizes deep learning to analyze student sentiment and predict classroom feedback, which improves teaching effectiveness and enhances students’ learning experience.

Student Sentiment Analysis and Classroom Feedback Prediction Using Deep Learning

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"Student Sentiment Analysis and Classroom Feedback Prediction Using Deep Learning"}

The application of deep learning is becoming a research hotspot in education, especially in student sentiment analysis and classroom feedback prediction....

Student Sentiment Analysis and Classroom Feedback Prediction Using Deep Learning

Online veröffentlicht: 03. Mai 2024

Seitenbereich: -

Eingereicht: 03. Apr. 2024

Akzeptiert: 18. Apr. 2024

DOI: https://doi.org/10.2478/amns-2024-0878

Schlüsselwörter
Deep learning, Student sentiment analysis, Classroom feedback prediction, MTCNN face detection

© 2024 Peisong Wang, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Student Sentiment Analysis and Classroom Feedback Prediction Using Deep Learning

Online veröffentlicht: 03. Mai 2024

Seitenbereich: -

Eingereicht: 03. Apr. 2024

Akzeptiert: 18. Apr. 2024

DOI: https://doi.org/10.2478/amns-2024-0878

SchlüsselwörterDeep learning, Student sentiment analysis, Classroom feedback prediction, MTCNN face detection

© 2024 Peisong Wang, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Deep learning, Student sentiment analysis, Classroom feedback prediction, MTCNN face detection