The Evaluation Emotional State of Students in the Classroom Using Artificial Intelligence Application
Article Sidebar
Main Article Content
Abstract
This research aims to create an application to assess students' emotions in the classroom to be tested using artificial intelligence with a sample of students aged 18 years old and over attending schools of the Vocational Education Commission. This application uses the faces of volunteers in Kanchanaburi and Nonthaburi provinces to train models with images from FER2013 and the sample group to test the application in Nakhon Nayok, Phichit and Khon Kaen provinces and in Bangkok. The application uses computer vision with Haar's facial detection algorithm and convolutional neural network (CNN) to make predictions. If the AI finds an emotion, it will count the frame and count the cumulative frequency of the seven emotions. The positive emotions include natural resting emotion, happiness, and surprise, while negative emotions include sadness, fear, anger, and disgust. The training model was programmed to allow artificial intelligence to analyse the learners’ faces. A webcam was connected to a portable computer while teaching in the classroom without recording video or sending data to be stored on an online server in order to protect the privacy of the volunteers. The research found that: 1) the application had an accuracy value of 0.6288 and interrater reliability value with an average accuracy of all emotional states of 0.8 and 2) the application trial found that room environments affected the face discrepancy recorded by the camera. The learners' actions affected the analysis of facial emotions, for instance some students wore masks. The assessment of the students' emotions showed that normal emotions were the most common and no students had the emotion of disgust. After analysing, it was found that positive moods accounted for 71.19% of all moods, while negative moods made up 28.81%. The AI application is able to generate a graph in real-time which can highlight if an individual student is consistently sad to prompt the teacher to help them. Moreover, teachers can use the graphs to improve teaching and learning.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The Journal of Information and Learning is operated by the Office of Academic Resources, Prince of Songkla University. All articles published in the journal are protected by Thailand copyright law. This copyright covers the exclusive rights to share, reproduce and distribute the article, including in electronic forms, reprints, translations, photographic reproductions, or similar. Authors own copyrights in the works they have created as well as the Office of Academic Resources. The Journal reserves the right to edit the language of papers accepted for publication for clarity and correctness, as well as to make formal changes to ensure compliance with the journal's guidelines. All authors must take public responsibility for the content of their paper.
References
Artino, A. R. (2012). Emotions in online learning environments: Introduction to the special issue. The Internet and Higher Education, 15(3), 137-140. https://doi.org/10.1016/j.iheduc.2012.04.001
Bouhlal, M., Aarika, K., AitAbdelouahid, R., Elfilali, S., & Benlahmar, E. (2020). Emotions recognition as innovative tool for improving students’ performance and learning approaches. Procedia Computer Science, 175, 597-602. https://doi.org/10.1016/J.PROCS.2020.07.086
Chandra, Y. (2021). Online education during COVID-19: perception of academic stress and emotional intelligence coping strategies among college students. Asian Education and Development Studies, 10(2), 229-238. https://doi.org/10.1108/AEDS-05-2020-0097
Chiurco, A., Frangella, J., Longo, F., Nicoletti, L., Padovano, A., Solina, V., Mirabelli, G., & Citraro, C. (2022). Real-time detection of worker’s emotions for advanced human-robot interaction during collaborative tasks in smart factories. Procedia Computer Science, 200, 1875-1884. https://doi.org/10.1016/J.PROCS.2022.01.388
FER-2013. (2020). Kaggle. https://www.kaggle.com/datasets/msambare/fer2013
Fredrickson, B. L. (1998). What good are positive emotions? Review of General Psychology, 2, 300-319. https://doi.org/10.1037/1089-2680.2.3.300
Hfocus. (2021, October 8). Pramœ̄n sukkhaphāp čhit dek læ wairun thai yok wā 1.8 sǣn rāi phop khrīat sūng yong sưmsao tit čhō̜ tit kēm ʻō̜ nalai māk khưn!! [Assessing the mental health of more than 180,000 Thai children and teenagers, found high stress and increased risk of depression. More addicted to the screen and online games!!]. Hfocus. https://www.hfocus.org/content/2021/10/23307
Hsieh, Y. H., & Huang, F. Y. (2020). The effects of a mindfulness curriculum on the emotional regulation and interpersonal relationships of fifth-grade children. Bulletin of Educational Psychology, 52(1), 25-49. https://doi.org/10.6251/BEP.202009_52(1).0002
Mohamed, A. A., Bilal, K. H., & Elmutasim, I. E. (2021). Face recognition by artificial neural network using MATLAB. 2021 IEEE 6th International Conference on Computing, Communication and Automation (ICCCA). https://ieeexplore.ieee.org/document/9666434
Nixon, D., Mallappa, V. V., Petli, V., HosgurMath, S., & Kiran K, S. (2022). A novel AI therapy for depression counseling using face emotion techniques. Global Transitions Proceedings. https://doi.org/10.1016/J.GLTP.2022.03.008
Plutchik, R. (2001). The nature of emotions: Human emotions have deep evolutionary roots, a fact that may explain their complexity and provide tools for clinical practice. American Scientist, 89, 344-350. https://www.academia.edu/43620307/The_Nature_of_Emotions_Plutchik_2001_
Ramsay, A., & Ahmad, T. (Ed.). (2023). Machine learning for emotion analysis in python. Packt Publishing.
Rasheed, L., Khadam, U., Majeed, S., Ramzan, S., Bashir, S., & Iqbal, M. (2022). Face recognition emotions detection using haar cascade classifier and convolutional neural network. https://doi.org/10.21203/rs.3.rs-2048290/v1
Reeja, S. R., Cherian, R., Waghmare, K., & Jothimani. (2021). EEG signal-based human emotion detection using an artificial neural network. Handbook of Decision Support Systems for Neurological Disorders (pp. 107-124). https://doi.org/10.1016/B978-0-12-822271-3.00007-4
Shin, J. G., Choi, G. Y., Hwang, H. J., & Kim, S. H. (2021). Evaluation of emotional satisfaction using questionnaires in voice-based human–ai interaction. Applied Sciences (Switzerland), 11(4), Article 1920. https://doi.org/10.3390/app11041920
Wongvanit, S. (2021). Design research in education (2nd ed., Vol. 1200). CU Press.
