Chameleons in Imagined Conversations: 

A new Approach to Understanding Coordination of Linguistic Style in Dialogs.

Cristian Danescu-Niculescu-Mizil and Lillian Lee.

Cognitive Modeling and Computational Linguistics Workshop at ACL 2011.


Featured on

Talk Slides

Data and Code available in ConvoKit: a toolkit for analyzing conversations (including the Cornell Movie--Dialogs Corpus)

Legacy dataset

Related Papers: 

                                     Echoes of power

                                     Mark my Words!




Conversational participants tend to immediately and unconsciously adapt to each other's language styles:  a speaker will even adjust the number of articles and other function words in their next utterance in response to the number in their partner's immediately preceding utterance. This striking level of coordination is thought to have arisen as a way to achieve social goals, such as gaining approval or emphasizing difference in status.  But has the adaptation mechanism become so deeply embedded in the language-generation process as to become a reflex?  We argue that fictional dialogs offer a way to study this question, since authors create the conversations but don't receive the social  benefits (rather, the imagined characters do).  Indeed, we find significant coordination across many families of function words in our large movie-script corpus. We also report suggestive preliminary findings on the effects of  gender and other features; e.g., surprisingly, for articles, on average, characters adapt more to females than to males.




  author={Cristian Danescu-Niculescu-Mizil and Lillian Lee},

  title={Chameleons in imagined conversations:

  A new approach to understanding coordination of linguistic style in dialogs.},

  booktitle={Proceedings of the

        Workshop on Cognitive Modeling and Computational Linguistics, ACL 2011},