@inproceedings{44deabe92a864328826f997bc1a0120a,
title = "Classification of distributed data using topic modeling and maximum variation sampling",
abstract = "From a management perspective, understanding the information that exists on a network and how it is distributed provides a critical advantage. This work explores the use of topic modeling as an approach to automatically determine the classes of information that exist on an organization's network, and then use the resultant topics as centroid vectors for the classification of individual documents in order to understand the distribution of information topics across the enterprise network. The approach is tested using the 20 Newsgroups dataset.",
author = "Patton, {Robert M.} and Beaver, {Justin M.} and Potok, {Thomas E.}",
year = "2011",
doi = "10.1109/HICSS.2011.101",
language = "English",
isbn = "9780769542829",
series = "Proceedings of the Annual Hawaii International Conference on System Sciences",
booktitle = "Proceedings of the 44th Annual Hawaii International Conference on System Sciences, HICSS-44 2010",
note = "44th Hawaii International Conference on System Sciences, HICSS-44 2010 ; Conference date: 04-01-2011 Through 07-01-2011",
}