preprints.org > social sciences > education > doi: 10.20944/preprints202401.1323.v1

Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Version 1 : Received: 29 December 2023 / Approved: 17 January 2024 / Online: 18 January 2024 (03:11:33 CET)

One of the needs of the teaching and learning processes is the lack of information during the process, such as the emotions of students. Emotions influence learning, the ability to process information and accurately understand what we are dealing with. They profoundly affect students’ academic engagement and performance. One new way of getting such information is monitoring students' emotions. This research aims to expose 6 groups of secondary school students to video recordings for further analysis and categorization of their emotions. A model of emotional recognition (ER) during classroom learning was designed, with a custom-made code, from recorded videos to images to identify faces, action units (AUs) and consequently the emotions of each of the students shown on the screen. In addition, the ER model was optimized, from detecting few students to many students during a class. Emotions were then analysed according to the academic year, subject, and comparing the emotions at the beginning and at the end of the class. The results indicate the presence of a variety of emotions in the classroom and we found significant differences in the presence of some emotions depending on the time of class, subject and academic year, although there are no clear patterns. We discussed how emotions influence students' academic performance, and we suggest future research focus on teachers utilizing tools like this to improve student well-being and performance.

image processing; emotion recognition; secondary school students; academic performance; students' emotions in learning; students well-being; Py-Feat

Social Sciences, Education

* All users must log in before leaving a comment