RT Conference Proceedings
T1 Vital Emo: The boredom detector with a machine learning perspective
A1 El-Yamri, Meriem
A1 Isar Muñoz, Diego
A1 Ortiz Marchut, Álvaro
A1 Padilla Rodríguez, Daniel
A1 Prieto Ibañez, Sofía
A1 Manero Iglesias, José Borja
A1 Ros Velasco, Josefa
A2 Asia-Pacific Society for Computers in Education, 
AB Boredom is one of the main problems found in 21st-century educational environments. Today's society is hyperconnected and exposes us to a large number of daily stimuli. This daily overstimulation can negatively affect students who are facing several hours of online classes (especially in the new context derived from 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. The most noticeable are the widening of the eyelids, the opening of the lips, and the gaze direction. As for posture, there are references to using the hand to support the head, maintaining a reclining posture, or hiding part of the face. Its counterpart, interest, can be reflected in patterns such as maintaining a wide-eyed gaze, smiling, or maintaining an upright posture.This paper presents the development, architecture, and evaluation of a tool called VITAL EMO. Through artificial intelligence (tra ined with facial patterns), this tool seeks: 1) to detect, through a camera, students' boredom, and 2) to alert teachers of this situation, allowing them to change the methodology or strategy to reengage the students on the spot. The creation of the dataset used to train the AI was carried out with 12 people. The participants took part telematically; each were recorded as they watched a video and answered questions about it. Despite using a small dataset, the study results show that it is possible to detect facial patterns associated with engagement and boredom, such as smiling, squinting, facial occlusion, or avoiding being directly in front of the camera. These results pave the way for future research with a larger dataset to increase the effectiveness of AI and further develop the VITAL EMO tool.
YR 2021
FD 2021-04-01
LK https://hdl.handle.net/20.500.14352/102782
UL https://hdl.handle.net/20.500.14352/102782
LA eng
DS Docta Complutense
RD 20 ago 2024