Background: Boredom is one of the main problems in 21st-century educational environments. Today’s society is hyperconnected and exposes us to many daily stimuli. This overstimulation can negatively affect students who are facing several hours of online classes, especially in the context of COVID-19. In these classes, students experience a shortage of stimuli, resulting in boredom and a shorter attention span. Past studies have shown that certain facial patterns help detect lack of engagement and boredom.
Methodology: This is a work-in-progress paper that presents the development, architecture, and evaluation of a tool called VITAL EMO. Through artificial intelligence (trained with facial patterns), this tool seeks 1) to detect, through a camera, students’ boredom, and 2) to alert teachers of this situation. The creation of the dataset used to train the AI was carried out with 12 people. The participants took part telematically. Each was recorded as they watched a video and answered questions about it.
Results: Despite using a small dataset, the study results show that it is possible to detect facial patterns associated with engagement and boredom. Online students’ faces are sufficient to detect characteristic patterns of boredom or engagement, but not to determine their degree with accuracy. Our artificial intelligence has managed to classify these states from explicit gestures, i.e., facial occlusion caused by the hand, smiling, having the eyes wide open, or facing the camera directly. According to the literature, these gestures represent typical boredom and engagement signals. In the case of holding the head with the hand, the trained AI tends to recognize boredom more easily when the person uses the left hand. This is due to a reduced dataset in which we have few images of people using the right hand to hold their head, even though both are clear patterns of boredom. The generated dataset is not large nor varied enough due to limited resources available. The authors would like to highlight one more time that this is a work-in-progress paper in which only preliminary results from a first developmental stage are presented, which does not mean this is not a valuable endeavor to be shared with the academic community.
Conclusion: This paper introduces an exploration of the boredom/engagement detection procedures that AI is making possible currently. Since the prospective work is focused on taking advantage of this knowledge to send the teacher information about the state in which their students are, we wanted with this paper to make a declaration of intentions to the specialists to open discussion and collaboration. The results pave the way for future research with a larger dataset to increase the effectiveness of AI and further develop the VITAL EMO tool.
- Manero-Iglesias, Borja, Associate Professor, Faculty of Computer Sciences, Complutense University of Madrid, firstname.lastname@example.org
- Ros-Velasco, Josefa, MSCA Postdoctoral Fellow in Boredom Studies, Faculty of Philosophy, Complutense University of Madrid, email@example.com
- El-Yamri, Meriem, Predoctoral Fellow in Computer Sciences, Faculty of Computer Sciences, Complutense University of Madrid, firstname.lastname@example.org
- Isar-Muñoz, Diego, BA in Computer Sciences, Faculty of Computer Sciences, Complutense University of Madrid, email@example.com
- Ortiz-Marchut, Álvaro, BA in Computer Sciences, Faculty of Computer Sciences, Complutense University of Madrid, firstname.lastname@example.org
- Padilla-Rodríguez, Daniel, BA in Computer Sciences, Faculty of Computer Sciences, Complutense University of Madrid, email@example.com
- Prieto-Ibáñez, Sofía, BA in Computer Sciences, Faculty of Computer Sciences, Complutense University of Madrid, firstname.lastname@example.org