Machine Learning - Special issue on learning with probabilistic representations
An introduction to variable and feature selection
The Journal of Machine Learning Research
Variable selection and ranking for analyzing automobile traffic accident data
Proceedings of the 2005 ACM symposium on Applied computing
Searching for interacting features
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Building classifiers using Bayesian networks
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 2
Proceedings of the 2011 Military Modeling & Simulation Symposium
Representing dynamic social networks in discrete event social simulation
Proceedings of the Winter Simulation Conference
Hi-index | 0.00 |
The representation of human behavior and cognition continues to challenge the modeling and simulation community. The use of survey and polling instruments to inform belief states, issue stances and action choice models provides a compelling means of developing models and simulations with empirical data. Using these types of data to population social simulations can greatly enhance the feasibility of validation efforts, the reusability of social and behavioral modeling frameworks, and the testable reliability of simulations. We provide a case study demonstrating these effects, document the use of survey data to develop cognitive models, and suggest future paths forward for social and behavioral modeling.