Agents that reduce work and information overload
Communications of the ACM
Using explicit requirements and metrics for interface agent user model correction
AGENTS '98 Proceedings of the second international conference on Autonomous agents
Principles of mixed-initiative user interfaces
Proceedings of the SIGCHI conference on Human Factors in Computing Systems
Maintenance of Discovered Association Rules in Large Databases: An Incremental Updating Technique
ICDE '96 Proceedings of the Twelfth International Conference on Data Engineering
Human-Computer Interaction
Building an expert travel agent as a software agent
Expert Systems with Applications: An International Journal
Enhancing the Interaction between Agents and Users
SBIA '08 Proceedings of the 19th Brazilian Symposium on Artificial Intelligence: Advances in Artificial Intelligence
An evaluation study of clustering algorithms in the scope of user communities assessment
Computers & Mathematics with Applications
Building respectful interface agents
International Journal of Human-Computer Studies
Artificial intelligence
SBNMA '11 Proceedings of the 2011 ACM workshop on Social and behavioural networked media access
Ontology-based user profile learning
Applied Intelligence
Exploiting user feedback for adapting mobile interaction obtrusiveness
UCAmI'12 Proceedings of the 6th international conference on Ubiquitous Computing and Ambient Intelligence
Hi-index | 0.01 |
Most people would welcome a personal assistant to help them with their work. When this help is embodied in a software assistant, however, many doubt the proposition's value. Past negative experiences with software assistants that interrupted them with irrelevant information or unnecessary suggestions leads many people to reject the concept outright. Software agents might also suggest actions when users prefer to find their own solutions, or warn users about problems when what they want is a solution. For software assistants to be acceptable, they must not only learn users' interests and priorities but also learn how to properly work and interact with users in different contexts. A new user-profiling approach personalizes and enhances the interaction between a user and his or her personal agent. This approach aims to design agents that provide context-aware assistance and make context-aware interruptions in a timely manner. This article is part of a special issue on AI, Agents, and the Web.