@inproceedings{5d52befea5924de9a75c53b3108a38a8,
title = "Machine learning for information architecture in a large governmental website",
abstract = "This paper describes ongoing research into the application of machine learning techniques for improving access to governmental information in complex digital libraries. Under the auspices of the GovStat Project, our goal is to identify a small number of semantically valid concepts that adequately spans the intellectual domain of a collection. The goal of this discovery is twofold. First we desire a practical aid for information architects. Second, automatically derived document-concept relationships are a necessary precondition for real-world deployment of many dynamic interfaces. The current study compares concept learning strategies based on three document representations: keywords, titles, and full-text. In statistical and user-based studies, human-created keywords provide significant improvements in concept learning over both title-only and full-text representations.",
keywords = "Information Architecture, Interface Design, Machine Learning",
author = "Miles Efron and Jonathan Elsas and Gary Marchionini and Junliang Zhang",
year = "2004",
doi = "10.1145/996350.996386",
language = "English (US)",
isbn = "1581138326",
series = "Proceedings of the ACM IEEE International Conference on Digital Libraries, JCDL 2004",
publisher = "Association for Computing Machinery",
pages = "151--159",
booktitle = "Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global Reach and Diverse Impact, JCDL 2004",
address = "United States",
note = "Proceedings of the Fourth ACM/IEEE Joint Conference on Digital Libraries; Global reach and Diverse Impact, JCDL 2004 ; Conference date: 07-06-2004 Through 11-06-2004",
}