EMOTION CHIP

We cracked the math underlying human social signaling

And patented the core machinery underlying emotional expressions

The missing link ​in affective computing

A - What does your customer'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 customer's emotional expression is a complicated challenge. But the power in doing so comes from understanding what the expressions actually mean, and thereby knowing how the software should respond. 

EMOTION CHIP technology addresses this issue, giving rigorous meanings to emotional expressions customizable for your business.

1. How satisfied is the customer about what just happened?
2. How relaxed is the customer about what just happened?
3. What does the customer want?
4. How serious is he about it?
5. What is the customer's current opinion about the software it is interacting with? 
6. How sure of himself is the customer?
7. How disagreeable is the customer's current response?
8. How much social capital has the customer put at risk, or feel he has bet, given his response?
9. To what extent has the interaction gotten "out of hand" (with a danger of embarrassment, and a lost customer)? 

B - What emotional expression does the customer think your software is expressing?

Whether or not your interactive software is designed to express emotions, it is often treated by the user as if it is an expressive agent. 

It would be nice to know what emotional expression your software appears to be expressing. Often you won't know, because you didn't design your software to express emotions at all. And even if you did, it is important to understand what expression the user takes your software to be expressing, which might well differ from your intent.

EMOTION CHIP technology solves this problem: emotional expressions have rich semantic meaning with multiple components, and one concerns the user’s interpretation of what he believes the other agent (in this case your software) expressed he wants.

Emotion recognition software with the EMOTION CHIP can thereby not only read the user’s expression, but can infer what emotional expression the user believes was expressed by the interactive software agent. (And this includes the nine semantic facets described in (A).)

The software can then use this information to modulate the software's behavior (maybe an advertisement) on the next interaction. But without this information, the software would not know what its own software even expressed in the opinion of the user. 

C - What class of algorithms underlies emotional artificial intelligence?

True intelligence is not about solving math and puzzles. What people really mean by intelligence is… social intelligence. Dope, fool, idiot, imbecile, moron, simpleton, etc. These imply social incompetency. An "idiot-savante" has genius level skills in some area, but lacks social competency. Intelligence is our capacity to be polite, to negotiate, to strategize, to raise the stakes, to push back, to compromise. With true social intelligence, humans are able to cooperate, compete, and even lead.

We all have to know our boundaries; how far we can "push" each individual in each kind of interaction. Learning these boundaries is what gives us an awareness of others. In the future, AI's fate -- like ours -- will be to navigate an ever-buffeting sea of crafty beings, and will accordingly need the other-awareness utterly missing in AI today.

It's not enough to have shallow face-recognition attribution and a veneer of human facial expression. AI must fully grasp the language of emotion: understand what each emotion means (see (A) and (B)), reason about what reply to make, and know which emotion signals that reply. 

EMOTION​ CHIP technology allows the construction of AI algorithms with emotional intelligence, and with customizable personalities that vary along socio-emotionally sensible dimensions. 

Such algorithms enable AI not only to comprehend emotional expressions, but also to negotiate, grasp etiquette, possess an awareness of status, and understand the manner in which signaling emotions commits one to bets of reputation (e.g., a trash talker is at greater risk than a polite person).

D - How to summarize an emotional expression in a low dimensional space, e.g., for extracting emotions from text?

To extract emotional expressions from text -- such as from customer support complaints -- traditional machine learning would require training on at least six dimensions, one for each of the six independent expressions: anger, sadness, fear, disgust, happiness and surprise. 

That leads to two big difficulties. 

First, because people mix multiple expressions together, that means there is a combinatorial explosion of possible expressive mixtures (729, in fact). It is therefore extremely cumbersome to manually tag text with the right emotion mixture, and difficult for machine learning to handle it even if manual tagging were possible. 

​Second, even if the many expressive mixtures can be recognized from text, with more than 700 qualitatively distinct expressions, what do they all mean in customer support terms? (See (A) above.)

EMOTION CHIP technology accommodates emotional expressions in a much lower dimensional space than traditional theories, requiring only two dimensions for tagging and learning. 

​But it is nevertheless theoretically rich, with 81 qualitatively distinct emotional expressions, each recognizable, with a rigorous quantitative meaning, and with the appropriate machinery underlying it.​

---

Related applications

Emotionally interactive software: Imagine advertisements that read the user’s emotional expressions and understand those expressions as offers in an implicit negotiation about how much of the advertisement the user is willing to watch in order to get to the service (e.g., an advertisement before the YouTube video service the user truly wants to see). EMOTION CHIP technology, for example, understands how to calculate the quantitative level of serious versus casual expressed in an emotion, and can thereby relate that to the interactive software agent. Without this information, the software may have no idea that it is about to lose its customer; or, alternatively, the software may not realize that the user is currently casual, and open to being shown more of the ad.

Online Haggling: Haggling in person works because you can perceive the level of seriousness, and thus the social cost to disagreement. Online, with just dollar amounts being volleyed back and forth, haggling is missing the full range of emotional expressions used in real life which helps negotiations come to a conclusion without dramatic swings and troll-like behavior. EMOTION CHIP technology has the machinery allowing online negotiation to include full emotional expressions (and with low dimensionality, see (D) above), regulating the participants' behavior, and allowing each to more honestly signal their actual beliefs about the fair price.

Having a discussion via emotions. What if you were able to express an emotion on social media capturing the richness of what you’re actually feeling? ...and with only a single button click on a palette? Imagine being able to have a conversation purely via emotional expressions. What if there could be a simple but powerful visualization of the state of a discussion thus far, capturing each party’s claim, pride, respectfulness, satisfaction level, relaxation level, seriousness, and disagreeableness? What if, say, Facebook could track whether the discussion led to agreement, and who was more correct? Suppose you could be given advanced explicit feedback on the meaning and implications of each emotional expression (e.g., how disagreeable you would be) before you express it. Imagine that the wider social network could more easily see each person’s social behavior, including how disagreeable he tends to be, and is thereby able to update its judgement about his reputation on that basis. ...like in real life where people tend to be much better behaved. What if Twitter could keep track of how disagreeable someone tends to be, or tends to be to certain individuals, and modulates the social network on that basis? EMOTION CHIP technology has the innovative — and transparent — machinery that, for the first time, allows technology as described in the above “what ifs”. 

Emotion-machine interface. Imagine two people working as a team, perhaps two tennis players playing doubles, or a pair of soldiers infiltrating an enemy base. When working together well, the two members become a single unit. And they achieve this level of “oneness” not by virtue of language, but by virtue of the emotional expressions they signal to one another. (Think: How do a pair of hunting dogs do it?) What if, say, you could be bound together with your motorcycle as a team working as one? What if you could effortlessly communicate with your motorcycle using natural emotional expressions? And what if your motorcycle could communicate with you in a natural emotional way that you understand “in your bones”? As our vehicles begin to have their own artificial intelligence, in order for the vehicle to work with the driver so as to be a single team, the vehicle must both understand the meaning of emotional expressions, and be able to signal them (perhaps by slight variations in the intonation of the engine’s “voice”, or via the visual feedback, or via variations in the tactile characteristics of the steering wheel or seat, or via …). EMOTION CHIP technology has the power to allow emotion-machine interfaces.

Home     Range     Who      Contact