Acknowledgements for Emotion Twenty Questions (EMO20Q)

The idea for the game of Emotion Twenty Questions (EMO20Q) evolved over a period of time, but followed several distinct phases.


Abe Kazemzadeh, a graduate student in computer science was visiting his former classmate, Nick Mote, at google for lunch. Lunch at google is known for both delicious food and lively conversation. During lunch another googler mentioned a plan for a universal ontology. Abe was reading Moby Dick at the time and the chapter "Cetology" presented a problem for having a universal ontology. Ishmail, the narrator of Moby Dick, and his sailor colleagues did not agree with Linneaus in classifying whales as fish:

Now the various species of whales need some sort of popular comprehensive classification, if only an easy outline one for the present, hereafter to be filled in all its departments by subsequent laborers. As no better man advances to take this matter in hand, I hereupon offer my own poor endeavors. I promise nothing complete; because any human thing supposed to be complete, must for that very reason infallibly be faulty. I shall not pretend to a minute anatomical description of the various species, or - in this place at least - to much of any description. My object here is simply to project the draught of a systematization of cetology. I am the architect, not the builder. But it is a ponderous task; no ordinary letter-sorter in the Post- office is equal to it. To grope down into the bottom of the sea after them; to have one's hands among the unspeakable foundations, ribs, and very pelvis of the world; this is a fearful thing. What am I that I should essay to hook the nose of this Leviathan! The awful tauntings in Job might well appal me. "Will he (the Leviathan) make a covenant with thee? Behold the hope of him is vain!" But I have swam through libraries and sailed through oceans; I have had to do with whales with these visible hands; I am in earnest; and I will try. There are some preliminaries to settle. First: The uncertain, unsettled condition of this science of Cetology is in the very vestibule attested by the fact, that in some quarters it still remains a moot point whether a whale be a fish. In his System of Nature, A. D. 1776, Linnaeus declares, "I hereby separate the whales from the fish." But of my own knowledge, I know that down to the year 1850, sharks and shad, alewives and herring, against Linnaeus's express edict, were still found dividing the possession of the same seas with the Leviathan. The grounds upon which Linnaeus would fain have banished the whales from the waters, he states as follows: "On account of their warm bilocular heart, their lungs, their movable eyelids, their hollow ears, penem intrantem feminam mammis lactantem," and finally, "ex lege naturae jure meritoque." I submitted all this to my friends Simeon Macey and Charley Coffin, of Nantucket, both messmates of mine in a certain voyage, and they united in the opinion that the reasons set forth were altogether insufficient. Charley profanely hinted they were humbug. Be it known that, waiving all argument, I take the good old fashioned ground that the whale is a fish, and call upon holy Jonah to back me. This fundamental thing settled, the next point is, in what internal respect does the whale differ from other fish. Above, Linnaeus has given you those items. But in brief, they are these: lungs and warm blood; whereas, all other fish are lungless and cold blooded.
This idea that people may disagree with a particular classification led to the idea that an ontology or system of classification should be person-specific. This does not mean that there is no "right" classification and everything is relative. However, a scientific theory, i.e., one that is "right" is not necessarily the theory that everyone has. When we say that a theory is "right" we are prescribing it, so it can be said to be "prescriptive". A theory that aims to describe how people think, conversely, would be called "descriptive". Later this idea would be tied to emotions.

It was not until the summer of 2010 that the idea of relative, subjective ontologies were applied to emotions. Abe was presenting work on a fuzzy logic model of emotions, based on Prof. Mendel's perceptual computing framework, at the world conference on computational intelligence (WCCI) in Barcelona. Abe also used the opportunity to visit a long lost-friend Rob Salgado and his wife Nantaa in Sitges, whose hospitality had enabled Abe, who had temporarily lost academic funding, to afford the travel costs. On the train rides from Sitges to Barcelona, they played Twenty Questions to pass the time. That was when it occurred to Abe to use emotions in the game of twenty questions as a way to observe people's subjective beliefs about emotions.


At first it was difficult to convince colleagues of the usefulness of EMO20Q in explaining how people describe emotions in natural language. However, one colleague, Panos Georgiou, saw the promise of EMO20Q and helped formulate the Boolean matrix representation of emotions versus questions. This paper about the Slashdot Zoo led to considering this boolean matrix to be a signed-matrix/graph. The formulation of the questions as propositions in a theory and emotions as theoretical entities was due primarily to Thomas Forster's engaging books on logic and secondarily to Prof. Len Adleman's course which got Abe interested in mathematical logic and Prof. Andrew Gordon's research into logically formalizing commonsense knowledge.


Experimentation with EMO20Q required rapidly deployable opensource chat technology and a team of players to work out the rules and refine the gameplay. Ejabberd was a clear choice for the XMPP chat functionality and the community of this software helped solve some initial misconceptions about how chat systems are implemented. The early play testers included friends, family, and labmates.