Human-Agent Dialogues and their Purposes

Baskar, Jayalakshmi; Lindgren, Helena

doi:10.1145/3121283.3121303

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The TUI agent and the companion agent are built using the BDI framework [11], providing each agent the basic constructs of intelligent agents: beliefs (the agent's knowledge about the user and a situation), desires (corresponding to its goals and their priorities), and intentions (corresponding to plans, also with priorities regarding how to act). The reason to build a distributed architecture including different agents is to allow the agents to have different belief bases and sets of goals and priorities, corresponding to their different purposes and roles [5,6]. The TUI agent's main role is to manage the TUI, interpret the sensor input data into information about the emotions, communicate sub-sets of the information to the actor repository available to the companion agent, and provide input to the companion agent that may activate its reasoning and acting.…”

Section: Proposed Agent Architecturementioning

confidence: 99%

Tangible Communication of Emotions with a Digital Companion for Managing Stress

Jingar

Lindgren

2019

Proceedings of the 7th International Conference on Human-Agent Interaction

Self Cite

View full text Add to dashboard Cite

The purpose of this research is to explore how an intelligent digital companion (agent) can support persons (human) with stress-related exhaustion to manage daily activities. In this paper, we explore in particular how information about a person's emotions can be communicated to the agent with means of non-verbal communication through tangible interfaces. The purpose is to explore how different individuals approach the task of designing their own tangible interfaces for communicating emotions with a digital companion, and the range of different preferences and expectations. Six participants were interviewed and created tangible prototypes during a co-creation workshop. The data was analysed using theories about human emotions and activity, and translated into a generic user model, an architecture for a multiagent system and interface design proposals. The results include increased understanding of how different individuals would like to express their emotions with tangible interfaces, and informed the design of the information models regarding representing emotions. The study illuminated the importance of personalisation of functionality and interface design to address the diversity among individuals, as well as the design of the adaptive behaviour of a digital companion. Future work includes further studies involving additional participants, the development of the stress management application and conducting user studies where prototypes are used in daily activities. CCS CONCEPTS • Human-centered computing → User models; Participatory design; Interface design prototyping; • Computing methodologies → Multi-agent systems; Intelligent agents.

show abstract

Section: Proposed Agent Architecturementioning

confidence: 99%