Skip to content
printicon

Socially Intelligent Systems for Person-Adapted Digital Coaching

PhD project This project is part of a larger research initiative on Socially Intelligent Systems including three PhD student projects and a postdoc project.

The aim of the research project is to develop socially intelligent software agents for person- adapted digital coaching.

Head of project

Helena Lindgren
Professor, senior lecturer (associate professor)
E-mail
Email

Project overview

Project period

2018-03-01 2022-02-28

Research subject

Computing science

Project description

The fundamental challenge lies in how intelligent autonomous agents may collaborate with humans in decision making tasks to achieve goals, and in making prioritizations among potentially conflicting goals, needs, motivations, preferences and choices of actions, e.g. in medical situations where healthcare professionals diagnose or select treatment methods. This is also highly important in situations where a person aims to change unhealthy behaviour, or needs to take action in order to reduce risk in work situations.

The aim of the research project is to develop socially intelligent software agents for person- adapted digital coaching. The project spans from fundamental theory development to validation in real-world applications. The fundamental development includes a complementary set of novel tools to be utilised by a cognitive companion for adaptation and collaboration purposes:

(1) dynamic multi-purpose motivational models that include emotional parameters and handle uncertainty;
(2) learning methods for capturing changes in user models, relating to motivation, goals, emotions, motives and activity;
(3) theoretical argumentation frameworks that define dialogues with different purposes and their relations in multi-purpose dialogues;
(4) methods for reasoning, utilising the semantic models and the learned interaction patterns, for reaching conclusions about the reasons for detected changes, and for selecting appropriate actions following the agent's goals relating to the human's motives and needs.

This is followed by a validation study of the approach in real-world use cases.