Real-time task recognition based on knowledge workers' computer activities

Authors:
Saskia Koldijk;Mark van Staalduinen;Mark Neerincx;Wessel Kraaij
Affiliations:
University Nijmegen, The Netherlands;TNO, The Netherlands;University Delft, The Netherlands;University Nijmegen, The Netherlands
Venue:
Proceedings of the 30th European Conference on Cognitive Ergonomics
Year:
2012

Citing 6
Cited 3

A diary study of task switching and interruptions

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Intelligent Human-Machine Interaction Based on Dynamic Bayesian Networks Probabilistic Intention Recognition

Journal of Intelligent and Robotic Systems
Logical Hierarchical Hidden Markov Models for Modeling User Activities

ILP '08 Proceedings of the 18th international conference on Inductive Logic Programming
UICO: an ontology-based user interaction context model for automatic task detection on the computer desktop

Proceedings of the 1st Workshop on Context, Information and Ontologies
The WEKA data mining software: an update

ACM SIGKDD Explorations Newsletter
A new model of plan recognition

UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence

Capturing context and mental state of knowledge workers

Proceedings of the 4th Information Interaction in Context Symposium
Supervision of learning methods in user data interpretation

Proceedings of the 4th Information Interaction in Context Symposium
Automatic recognition of context and stress to support knowledge workers

Proceedings of the 30th European Conference on Cognitive Ergonomics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Motivation -- Supporting knowledge workers in their self-management by providing them overviews of performed tasks. Research approach -- Computer interaction data of knowledge workers was logged during their work. For each user different classifiers were trained and compared on their performance on recognizing 12 specified tasks. Findings/Design -- After only a few hours of training data reasonable classification accuracy can be achieved. There was not one classifier that suited all users best. Take away message -- Task recognition based on knowledge workers' computer activities is feasible with little training, although personalization is an important issue.