image2
image3
image4
image5
image6
image7
image1

A Multilayer Personality Model

Kshirsagar, S. and Magnenat-Thalmann, N.


Abstract: Virtual humans have been the focus of computer graphics research for several years now. The amalgamation of computer graphics and artificial intelligence has lead to the possibility of creating believable virtual personalities. The focus has shifted from modeling and animation towards imparting personalities to virtual humans. The aim is to create virtual humans that can interact spontaneously using a natural language, emotions and gestures. This paper discusses a system that allows the design of personality for emotional virtual human. We adopt the Five Factor Model (FFM) of personality from psychology studies. To realize the model, we use Bayesian Belief Network. We introduce a layered approach for modeling personality, moods and emotions. In order to demonstrate a virtual human with emotional personality, we integrate the system into a chat application. Thus, the system enables the developer to design and implement personalities and enables the user to interact with them.


@inproceedings{1,
  booktitle = {Proceedings of 2nd International Symposium on Smart Graphics},
  author = {Kshirsagar, S. and Magnenat-Thalmann, N.},
  title = {A Multilayer Personality Model},
  pages = {107-115},
  month = jun,
  year = {2002},
  topic = {Facial Animation}
}