W3C home > Mailing lists > Public > public-xg-emotion@w3.org > May 2008

Re: [EMOXG] Deliverable report published as first draft: EmotionMarkup Language: Requirements with Priorities

From: Marc Schroeder <schroed@dfki.de>
Date: Thu, 08 May 2008 10:24:05 +0200
Message-ID: <4822B8A5.6060207@dfki.de>
To: pelachaud@iut.univ-paris8.fr
CC: ian@emotionai.com, public-xg-emotion@w3.org

Ian, Catherine, all,

the discussion on action tendencies is interesting. There seems to be 
agreement that in principle, for a system that is capable of acting (in 
some way) an emotion model should provide the possibility to specify the 
action tendencies linked to the emotion.

At the same time, very few systems implement this today.

pelachaud@iut.univ-paris8.fr schrieb:
> should the language we are working on
> deal solely with current state of the art, or look at the future and thus
> embed more information than our current systems can consider?
> The second approach is of course more interesting. However we should
> wander how we will validate it.

In this particular case I think it is relatively simple. Maybe we can 
agree on a basic way of representing action tendencies, in particular 
the question: are they categories or scales? -> Maybe scales, specifying 
how strong the tendency towards the given action is?

As for categories, dimensions, and appraisals, we could then leave the 
concrete set of action tendencies to the user; we would only specify 
some default set. Can anyone advise, maybe the Frijda books contain a 
limited collection of "typical" kinds of action tendencies?

If we can agree on the basic representation, then including action 
tendencies in the spec would not be difficult, so I would be OK to add 
it in the "mandatory" section.

What do people think?


Dr. Marc Schröder, Senior Researcher at DFKI GmbH
Coordinator EU FP7 Project SEMAINE http://www.semaine-project.eu
Chair W3C Emotion ML Incubator http://www.w3.org/2005/Incubator/emotion
Portal Editor http://emotion-research.net
Team Leader DFKI Speech Group http://mary.dfki.de
Project Leader DFG project PAVOQUE http://mary.dfki.de/pavoque

Homepage: http://www.dfki.de/~schroed
Email: schroed@dfki.de
Phone: +49-681-302-5303
Postal address: DFKI GmbH, Campus D3_2, Stuhlsatzenhausweg 3, D-66123 
Saarbrücken, Germany
Official DFKI coordinates:
Deutsches Forschungszentrum fuer Kuenstliche Intelligenz GmbH
Trippstadter Strasse 122, D-67663 Kaiserslautern, Germany
Prof. Dr. Dr. h.c. mult. Wolfgang Wahlster (Vorsitzender)
Dr. Walter Olthoff
Vorsitzender des Aufsichtsrats: Prof. Dr. h.c. Hans A. Aukes
Amtsgericht Kaiserslautern, HRB 2313
Received on Thursday, 8 May 2008 08:24:48 UTC

This archive was generated by hypermail 2.3.1 : Tuesday, 6 January 2015 19:52:15 UTC