Social Attitudes: Investigations with Agent Simulations Using Webots

This article presents a multi-agent simulation environment for studying agents' sociopolitical attitudes. It departs from a previously proposed concept of agents with sociopolitical attitudes, a high-level theoretical & conceptual model proposed by Petric et al (2002) that was intended for conversational agents. In contrast, our work pursues a bottom-up simulation philosophy where attitudes are grounded in sensory-motor behavior of spatially distributed autonomous agents, modeled in Webots simulation software. The original model was extended by defining an agent's sociopolitical type by means of weighting the three components found in the Petric et al (2002) model (neoliberal, alternative, & fundamentalist), thus allowing the creation of mixed sociopolitical types. Also, in the simulations performed, issues were modeled as agents with variable levels of importance. Moreover, we introduced inter-agent communication capable of causing changes in sociopolitical types. Results are presented & discussed with respect to the initial research questions. According to our experimental results the following parameters did not have any significant impact on the simulation outcomes: initial physical position & orientation of the agents, positions of the issues, the issues' dynamics, & inter-agent communication. Experiments with different initial agent types showed that agents with indeterminate sociopolitical types tended to change to neoliberal, alternative, or fundamentalist agents. We conclude by proposing future extensions of the model. Our work is related to a trend in the Artificial Intelligence community which is not primarily task or problem-solving oriented, but rather focuses on the study of the embodied & situated nature of social behavior in humans. 10 Tables, 15 Figures. Adapted from the source document.