What does your consumer's emotional expression mean in the context of your business?
Most affective computing systems today include (at least) six dimensions -- anger, sadness, fear, disgust, happiness and surprise. Because people can mix multiple expressions together, that would mean there is a combinatorial explosion of possible expressive mixtures (729, in fact). But what do these more than 700 expressions actually mean?
Building software to recognize a consumer’s emotional expression is a complicated challenge. But the power in doing so comes from understanding what the expressions mean, and thereby knowing how the software should respond.
EMOTION CHIP technology addresses this issue, giving rigorous meanings to emotional expressions customizable to your business.
What emotional expression does the consumer think your software is expressing?
Whether or not your software is designed to express emotions, its behavior is often treated by the user as if it is an expressive agent, and the user perceives it to be expressing an emotion on the basis of the way the agent behaviorally interacts.
But what emotion is the interactive software agent actually expressing? The designers of the interactive software agent may not even know because (a) they didn't design it to have one, (b) it is a highly non-trivial issue, and (c) there is probably considerable variability in how users interpret the agent behavior as emotional expressions.
Our EMOTION CHIP technology solves this problem: emotional expressions have more than one component, and one of them concerns the user’s interpretation of what he believes the agent expressed he wants (and the other concerns what the user himself wants). Emotion recognition software that understands the underlying semantic structure of emotional expressions can thereby read the user’s expression, and infer what emotional expression the user believes was expressed by the interactive software agent. The software can then use this information to modulate the agent behavior (e.g., advertisement) on the next interaction. But without this information, the software would not know what its own agent even expressed in the opinion of the user.