Previous research has shown that users prefer human-computer interfaces that match their own personality traits (Nass and Lee 2001).  Based on studies on personality and language use (Pennebaker and King 1999, Gill and Oberlander 2002--2004), we identified a set of textual features that indicate an utterance's underlying personality.  We now want to apply these features for the generation of text with recognizable personality.
 
In this talk, I will present a framework for generating dialogue in which two computer characters discuss a movie.  The characters are parameterized for personality, and their utterances are chosen from a pre-defined corpus.  Content and surface form of potential utterances are ranked for personality, making use of the FLIGHTS user modeling component (Foster and White 2003).
 
This PhD work is part of the Edinburgh-Stanford Link project Critical Agent Dialogue (CrAg).