Increasing users' trust on personal assistance software using a domain-neutral high-level user model

Authors:
Ingrid Nunes;Simone D. J. Barbosa;Carlos J. P. De Lucena
Affiliations:
PUC-Rio, Computer Science Department, LES, Rio de Janeiro, Brazil;PUC-Rio, Computer Science Department, LES, Rio de Janeiro, Brazil;PUC-Rio, Computer Science Department, LES, Rio de Janeiro, Brazil
Venue:
ISoLA'10 Proceedings of the 4th international conference on Leveraging applications of formal methods, verification, and validation - Volume Part I
Year:
2010

Citing 8
Cited 0

Agents that reduce work and information overload

Communications of the ACM
Multiagent systems: a modern approach to distributed artificial intelligence

Multiagent systems: a modern approach to distributed artificial intelligence
A framework for expressing and combining preferences

SIGMOD '00 Proceedings of the 2000 ACM SIGMOD international conference on Management of data
User - interface agent interaction: personalization issues

International Journal of Human-Computer Studies
Software Product Line Engineering: Foundations, Principles and Techniques

Software Product Line Engineering: Foundations, Principles and Techniques
Deploying a personalized time management agent

AAMAS '06 Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
From Belief Change to Preference Change

Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
CP-nets: a tool for representing and reasoning with conditional ceteris paribus preference statements

Journal of Artificial Intelligence Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

People delegate tasks only if they trust the one that is going to execute them, who can be a person or a system. Current approaches mostly focus on creating methods (elicitation approaches or learning algorithms) that aim at increasing the accuracy of (internal) user models. However, the existence of a chance of a method giving a wrong answer decreases users' trust on software systems, thus preventing the task delegation. We aim at increasing users' trust on personal assistance software based on agents by exposing a high-level user model to users, which brings two main advantages: (i) users are able to understand and verify how the system is modeling them (transparency); and (ii) it empowers users to control and make adjustments on their agents. This paper focuses on describing a domain-neutral user metamodel, which allows instantiating high-level user models with configurations and preferences. In addition, we present a two-level software architecture that supports the development of systems with high-level user models and a mechanism that keeps this model consistent with the underlying implementation.