In the field of artificial intelligence, affective computing refers to the collection of data from faces, body language or voice images to measure human emotions. Affective computing is also known as Emotion Artificial Intelligence.
According to the idea of the research area, Affective Computing should contribute to humanize the interaction with machines and AI and to take away the users’ fear of contact. At present, human-machine interaction often still seems very wooden, but such programs should enable machines to better adapt to the situation in order to react accordingly.
One example that is often mentioned here is the use of artificial intelligence in the education sector. If the student is frustrated by the teaching material, the machine can recognize this mood thanks to Emotion AI and react accordingly. Similarly, the teacher would do the same.
The potential for affective computing is broad. In medicine as well as in the use of AI and robotics in retail, “emotional” machines can optimally adapt to patients and customers and improve interaction with them.
The collection of emotions, such as facial expressions, muscle tension, posture, heart rate, pupil dilation or body temperature, is made possible by sensors, cameras, deep learning and big data.
Affective Computing will further bridge the gap between human emotion and the machine, allowing humans to have more confidence in robotics and AI.