Information Technology Reference
In-Depth Information
Familiarity is one variable that is stored in the agent's memory and will be remem-
bered in future interactions. Luck perception is also stored in memory, so the agent
can assess and comment if a player was lucky in previous games. Like/Dislike vari-
ables are also stored so the robot discloses, for instance, that it holds a “grudge”
against a particular player, because of previous games. The last data that is stored
in memory are the results and dates of previous matches. This type of data is often
mentioned in the beginning of the interaction, where the robot says for example:
“One week ago I lost against all of you, this time I am going to win!”.
7.4.5
Simulate Social Roles
In our observations of users playing Risk, we have indeed noticed that users use social
roles and change between them throughout the game. Examples included players that
in one phase of a game were exhibiting a Helper social role (actively helping another
player without seeking any in-game benefit) and in later parts of the game a violator
role towards the same player (giving up in the game and trying to destroy another
player just because of an argument).
Risk is a highly social game that supports various social roles in its gameplay.
However, we did not designed our social opponent to play specific social roles. The
roles appear naturally by using our appraisal variables to influence the robot's social
behaviour. For example, when the agent “likes” other players it often demonstrates
the social role of helper by saying encouraging comments such as “It went well
this turn!”. Also, when the agent has a great advantage (high power) over the other
players it is also more likely to adopt the dominator role by for example threatening
other players.
7.5
Conclusions
By taking considerations from our previous design experience with board game
opponents, research on the contributing factors for social presence, state-of-the-art
research in socially intelligent agents and long term interaction with social agents,
we present a scenario where a social agent has the capacity of being perceived as
more socially present by complying with a set of five guidelines.
These guidelines are presented in this paper, and by applying them to our partic-
ular scenario, we created a physically embodied artificial opponent that is able to
engage users in face-to-face interactions, has an emotion system used for exhibiting
believable verbal and non-verbal behaviours, is able to recognise, greet and remem-
ber users, and uses all of these capabilities to simulate common board game social
roles.
We believe that the guidelines proposed in this article can contribute to the creation
of the next generation of board game opponents.
