- When "I" Becomes "We": Modelling Dynamic Identity on Autonomous AgentsJoana Dimas, Inês Lobo, Samuel Mascarenhas, and 2 more authors[Under Review] 2022
Individuals change who they are in response to their social environment. In other words, one’s identity is dynamic, varying according to the context (e.g., individuals present, place, task). Identity has a significant impact on a person’s behaviour. Researchers have been interested in understanding howcontextual aspects shape identity and, in turn, how identity influences behaviour. Agent-based simulation models are great tools to identify and predict behaviour associated with these identity processes. In addition, agents can employ identity-related mechanisms based on social theories to become more socially believable and humanlike. The Social Identity Approach (SIA) is one of the most influential theories covering the social aspects of one’s identity, with many of its concepts being applied in social simulation research. This paper formalizes the Dynamic Identity Model for Agents (DIMA), an existing agent-based model based on SIA, providing a detailed theoretical foundation of the model, as well as an overview of its integration as a component into a social agent architecture. In DIMA, agents perceive themselves either as distinct individuals (personal identity) or as members of a social group (social identity), acting according to their context-dependent active identity. A simulation scenario based on the Dictator Game is presented to illustrate the use of the model. This work aims to guide other researchers who want to enhance their agents with the DIMA’s identity salience mechanism. As a result, theywould not only be able to assess howthis mechanism influences behaviour based on the context, but they would also be able to explore the dynamics between personal and social identities.
- Socially Aware Interactions: From Dialogue Trees to Natural Language Dialogue SystemsInês Lobo, Diogo Rato, Rui Prada, and 1 more authorIn International Workshop on Chatbot Research and Design 2021
In this paper, we present a prototype of a human-agent dialogue system, in which the scenarios are easy-to-author, as in tree-based dialogue tools. These, however, only allow for scripted and restricted dialogues. For this reason, we focused on developing a flexible and robust deliberation mechanism as well, based on the Cognitive Social Frames model and the theory of social practices, so that the conversational agent could provide acceptable responses according to different social contexts. Having access to sequences of frames containing small dialogue trees, the agent activates the most salient frame to reply appropriately to the user’s input. As a proof of concept, we designed a medical diagnosis scenario between a doctor and a patient in which the agent could play both roles given different settings of the scenario. In this prototype, the user had to choose from a limited set of alternatives, based on the current context, in order to respond to the agent; however, in the future, we intend to allow users to write freely, expecting to be able to map their utterances to the appropriate context.