Information Technology Reference
In-Depth Information
et al.
1995
). In Andre Pereira and Paiva (
2011
), we analysed the verbal communica-
tion in a board game and identified the most relevant categories to simulate dialogue
in an artificial opponent.
Non-verbal behaviour is used for communication, signalling and for social co-
ordination. This kind of natural social behaviour can be interpreted by humans
without the need to learn something new. As such, a human-like computer that
can express patterned non-verbal behaviours can cause social facilitation in users.
Believable non-verbal behaviours can show autonomy and contribute to the feeling
of social presence towards an agent. In robots or screen characters, having a respon-
sive real time gaze system can alone produce a high sense of agency and increase
the agent's perceived social presence (Yoshikawa et al.
2006
).
Besides choosing the best move to play, artificial opponents should grab players'
attention by using both verbal and non-verbal behaviours. An opponent can for
example show a sad expression attached with a sad speech when losing and a pride
expression associated with an excited speech when winning. Showing these kind
of behaviours should increase interactivity and realism (see Sect.
7.2.1
) and users
should be able to attribute mental states towards the artificial opponent and perceive
it as a social entity.
7.3.3
Emotion or Appraisal System
Emotion is a relevant topic in multiple disciplines such as philosophy, psychology,
neuroscience, machine learning and, most recently, in affective computing (Picard
2000
). It is universally recognized that emotions have a powerful influence in our
decision-making (Damasio
1994
). The same holds true when players make decisions
while playing board games, they let their emotions take part in their decision pro-
cess. Appraisal theories seem like the best alternative for influencing the decision
process with emotions and for generating emotional behaviour in an artificial op-
ponent. Appraisal is an evaluation of the personal significance of events as central
antecedents of emotional experience. Appraisal theories specify a set of criteria or
dimensions that are presumed to underlie the emotion constituent appraisal process.
These theories (Lazarus and Folkman
1984
; Sander et al.
2005
; Scherer
2001
) are
built upon studying our brain processes and the difficulty of simulating appraisal
models in computers is related to the complexity of the mental structures that need
to be simulated. However, some projects (Aylett et al.
2005
; Bartneck
2002
; Paiva
et al.
2004
) already successfully used an appraisal model, the OCC model (Ortony
et al.
1990
), to simulate human cognitive processes in their applications.
In our previous work, a social robot provided feedback on the users's moves
by employing facial expressions determined by the robot's appraisal system. This
appraisal system was composed by an anticipatory mechanism that created expecta-
tions on children's upcoming moves, and then based on the evaluation of the actual
move played by children, an affective state was elicited, resulting in different facial
expressions for the robot. It was shown that the emotional behaviour expressed by
this social robot increased the user's understanding of the game (Leite et al.
2008
).
