The computer program that detects your boredom as the future of education
Detecting boredom is already possible thanks to the use of cognitive computing, which can completely change areas such as education.
There are states of mind that human beings have a hard time not showing physically. Above all, those in which passivity in the face of the events that a person is experiencing is manifest. Among young people, for example, it is common to get bored in class, either due to lack of attraction to the subject, or due to fatigue, etc. The explosion in the use of algorithms for the recognition of all kinds of details in photographs and videos, together with the birth of the «affective computing“Has made it possible for MIT to detect boredom in real time.
What applications will this have for day to day? A very clear one is education. As read in novels like “Ready Player One”, the future of learning is perhaps far from physical classrooms, and near virtual classrooms. A context in which virtual reality dominates may be one in which students can study in great detail from home. Without reaching these extremes, there is already distance education where any factor that increases communication between teachers and students is crucial. Thanks to detecting students’ boredom, teachers can motivate them with certain techniques, or simply draw attention in some way.
Of course, the software will go further, and will be able to detect changes in mood, fear, satisfaction, etc. MIT’s approach has crystallized into Tega, a robot powered by a smartphone that is capable of analyzing emotions and teaching students accordingly. That is, it is capable of detecting boredom and acting more effusively, or of doing it with states of euphoria and trying to reduce it.
If this is integrated into the main personal assistants that already exist in smartphones and home robots, such as Siri, Cortana, Google Assistant or Amazon Echo, the possibilities are endless, since the “help” and interaction can be much more proactive, the objective end of these services. Since their arrival in 2011, they have been focused on answering questions or wishes, but thanks to deep learning and the huge amounts of data they are collecting, they have become very complex and, with it, become much more useful.
Main image: eltpics (Flickr)