I’ve started to do some further analysis on computation models of emotions and how they relate to cognition. The conjecture is that as emotions are fast and instinctual, a correspondingly fast implementation could be based on a classifier designed as a feed-forward discrimination network. There are a lot of questions to resolve, see attached diagram for an indication of the challenges*. A good way forward would be to identify some scenarios that illustrate the different aspects and some typical emotions, and which provide a means to ground discussion in concrete examples. My aim is to make computing just a little more human, i.e. warm and understanding rather than cold and emotionless!
Is anyone interested in helping to draft some scenarios and simple natural language dialogues for this?
* From https://www.frontiersin.org/articles/10.3389/fpsyg.2017.01454/full
Dave Raggett <dsr@w3.org> http://www.w3.org/People/Raggett
W3C Data Activity Lead & W3C champion for the Web of things
