@inproceedings{2aecd0f7deda4d10b557d9b0205a0416,
title = "Creating and exploring web form repositories",
abstract = "We present DeepPeep (http://www.deeppeep.org), a new system for discovering, organizing and analyzing Web forms. DeepPeep allows users to explore the entry points to hidden-Web sites whose contents are out of reach for traditional search engines. Besides demonstrating important features of DeepPeep and describing the infrastructure we used to build the system, we will show how this infrastructure can be used to create form collections and form search engines for different domains. We also present the analysis component of DeepPeep which allows users to explore and visualize information in form repositories, helping them not only to better search and understand forms in different domains, but also to refine the form gathering process.",
keywords = "focused crawling, hidden web, learning classifiers, search engines, web forms",
author = "Luciano Barbosa and Hoa Nguyen and Thanh Nguyen and Ramesh Pinnamaneni and Juliana Freire",
year = "2010",
doi = "10.1145/1807167.1807311",
language = "English (US)",
isbn = "9781450300322",
series = "Proceedings of the ACM SIGMOD International Conference on Management of Data",
pages = "1175--1177",
booktitle = "Proceedings of the 2010 International Conference on Management of Data, SIGMOD '10",
note = "2010 International Conference on Management of Data, SIGMOD '10 ; Conference date: 06-06-2010 Through 11-06-2010",
}