Affective computing is the field concerned with systems that recognise, interpret, simulate or respond to human emotion. The term was coined by Rosalind Picard at MIT in 1995.
What it is
It spans recognition (inferring emotional state from facial expression, voice, text or physiological signals), generation (systems that display affect), and adaptation (systems that change behaviour based on inferred emotion).
In learning technology the recognition strand dominates, usually via facial expression analysis, sometimes via physiological sensors in research settings.
Why it matters
It is the academic parent field of everything marketed as 'emotion AI'. Its literature is also where the honest discussion of limitations lives — accuracy ceilings, cultural variance and the contested basic-emotion model are all extensively debated in the research even where they are absent from vendor material.
A common confusion
Affective computing is a research field; emotion AI is largely a commercial label for a subset of it. The terms are used interchangeably in marketing and are not equivalent in scope.
Related
See also emotion ai, facial action coding system (facs) and valence and arousal. See the full glossary for the rest, or the limits of facial emotion recognition for the wider context.
See where your content loses people
Book a walkthrough and we will show you the engagement data on your own content.