Pilot study of real-time Emotional Recognition technology for Secondary school students

Cèlia Llurba,Gabriela Fretes, Ramon Palau
pp.  61 – 80, download


The large variety of students in a class makes the teaching task complex, making it difficult for the teacher to personalise learning to each student. Since students should be at the centre of the educational process, it is necessary to know them better, so this study aims to explore the possibilities of using a camera for emotion recognition (ER) with a view to the potential use of this information to improve the teaching-learning process. To accomplish the aim it is previously necessary to develop and apply code capable of detecting faces, ER and transfer this data into a database for further analysis, which consists of establishing the first approximations to the relationship between students’ emotions and other conditions (subject, time of day, academic performance). By monitoring the emotional state of students, if used properly, can improve educational processes, such as the teacher’s decision-making in the classroom, as well as optimise attention to students, adjusting their methodology or focusing on a specific student.

Keywords: emotion recognition; learning process; teaching; database; artificial intelligence; learning analytics


1.    Jackson, P. W. (2002) Práctica de la enseñanza. Buenos Aires: Amorrortu.
2.    Fisette, J. Getting to Know Your Students. Taylor & Francis Group , 81(7), pp. 42–49 (2013). https://doi.org/10.1080/07303084.2010.10598508
3.    Palau, R., Fuentes, M., Mogas, J. & Cebrián, G.. Analysis of the implementation of   teaching and learning processes at Catalan schools during the Covid-19 lockdown. Technology, Pedagogy and Education, 30(1) 183-199 (2021). 
4.    Ross, P. & Maynard, K. Towards a 4th industrial revolution, Intelligent Buildings International, 13(3), 159-161. (2021).https://doi.org/10.1080/17508975.2021.1873625
5.    Maturana, H. Emociones y lenguaje en educación y política. Dolmen. Santiago (1990).
6.    Maturana, H. El sentido de lo humano. Hachette. Santiago (1992).
7.    Ekman, P., Friesen W.V., & Ellsworth, P.. Emotion in the Human Face, ed., second ed. Cambridge Univ. Press (1982).   
8.    Ekman, P., O’Sullivan, M., Friesen, W.V & Scherer, K.R. Invited article: Face, voice, and body in detecting deceit. Journal of Nonverbal Behavior 15, 125–135 (1991).https://doi.org/10.1007/BF00998267
9.    Zeng, Z., Pantic, M.,  Roisman, G.I & Huang, T.S. A Survey of Affect Recognition Methods: Audio, Visual, and Spontaneous Expressions, in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 1, pp. 39-58 (2009).
10.  Caballo, V. E. Manual de evaluación y entrenamiento de las habilidades sociales. Madrid:  Siglo XXI (1993).
11.  Le-Quang, B. L., Dao, M. S., & Nazmudeen, M. S. H.. Wemotion: A System to Detect Emotion Using Wristbands and Smartphones. Communications in Computer and Information Science, 968, 92–103 (2018). https://doi.org/10.1007/978-981-13-5758-9_8
12.  Tan, J., Mao, J., Jiang, Y., & Gao, M.The Influence of Academic Emotions on Learning Effects: A Systematic Review’, International Journal of Environmental Research and Public Health 2021, Vol. 18, Page 9678. Multidisciplinary Digital Publishing Institute, 18(18), p. 9678 (2021). https://doi.org/10.3390/ijerph18189678
13.  Pekrun, R. The control-value theory of achievement emotions: Assumptions, corollaries, and implications for educational research and practice. Educational Psychology Review, 18(4), 315–341. (2006). https://doi.org/10.1007/s10648-006-9029-9
14.  Hossain, M. S., & Muhammad, G. Emotion recognition using deep learning approach from audio–visual emotional big data. Information Fusion, 49, 69–78(2019).
15.  Boulton, H., Brown, D., Standen, P., Belmonte, M., Kwiatkowska, G., Hughes-Roberts, T., & Taheri, M. Multi-modalities in classroom learning environments. INTED2018 Proceedings, 1, 1542–1547 (2018). https://doi.org/10.21125/inted.2018.0264
16.  Choppin, J. Data Use in Practice: Examples from the School Level Investigating Teaching  Candidates’ Experiences with Early edTPA Implementation View project Developing Principles for Mathematics Curriculum Design and Use in the Common Core Era (ERGO) View project. (2022).
17.  Marsh, J. A., Pane, J. F., & Hamilton, L. S. Making Sense of Data-Driven Decision  Making in Education: Evidence from Recent RAND Research. Occasional Paper. RAND Corporation (2006).
18.  Choi, D. Y., & Song, B. C. Semi-Supervised Learning for Continuous Emotion Recognition Based on Metric Learning. IEEE Access, 8, 113443–113455 (2020).
19.  Altrabsheh, N., Cocea, M., Fallahkhair, S. Learning Sentiment from Students’ Feedback for Real-Time Interventions in Classrooms. International Conference on Adaptive and Intelligent Systems (2014). https://doi.org/10.1007/978-3-319-11298-5_5
20.  Edwards, F. Early to rise? The effect of daily start times on academic performance.Economics of Education Review 31, 970-983 (2012).
21.  Pope, N.G. How the Time of Day Affects Productivity: Evidence from School Schedules. Review of Economics and Statistics 98:1, 1-11. (2016). https://doi.org/10.1162/REST_a_00525
22. Balart, P. Rendimiento y horario en las pruebas de conocimiento: evidencia de la Educación Superior. Fundación Ramón Areces y Fundación Europea Sociedad y Educación. (2021).
23.  Martínez-Sierra, G., & García-González, M. Students’ Emotions in the High School Mathematics Class: Appraisals in Terms of a Structure of Goals. International Journal of  Science and Mathematics Education, 2(15), 349−369. (2017).
24.  Paoloni, P., & Vaja, A. Achievement emotions in assessment contexts: an exploratory study with university students. Innovación Educativa, 13(62), 135−159. (2013).
25.  OECD, Education at a Glance 2021: OECD Indicators, OECD Publishing, Paris, (2021).
26.  Mogas, J. & Palau, R. Smart Classrooms i l’adveniment de la Quarta Revolució Industrial: anàlisi dels factors clau per al disseny d’aules intel·ligents. [Doctoral dissertation, Universitat Rovira i Virgili] (2020).

back to Table of Contents