@inproceedings{061d5ee3b8f94dc8919c9ad5690ca33a,
title = "Finding pages on the unarchived Web",
abstract = "Web archives preserve the fast changing Web, yet are highly incomplete due to crawling restrictions, crawling depth and frequency, or restrictive selection policies - most of the Web is unarchived and therefore lost to posterity. In this paper, we propose an approach to recover significant parts of the unarchived Web, by reconstructing descriptions of these pages based on links and anchors in the set of crawled pages, and experiment with this approach on the DutchWeb archive. Our main findings are threefold. First, the crawled Web contains evidence of a remarkable number of unarchived pages and websites, potentially dramatically increasing the coverage of theWeb archive. Second, the link and anchor descriptions have a highly skewed distribution: popular pages such as home pages have more terms, but the richness tapers off quickly. Third, the succinct representation is generally rich enough to uniquely identify pages on the unarchived Web: in a known-item search setting we can retrieve these pages within the first ranks on average.",
keywords = "Anchor text, Information retrieval, Link evidence, Web archives, Web archiving, Web crawlers",
author = "Huurdeman, \{Hugo C.\} and Anat Ben-David and Jaap Kamps and Thaer Samar and \{De Vries\}, \{Arjen P.\}",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 14th IEEE/ACM Joint Conference on Digital Libraries, JCDL 2014 ; Conference date: 08-09-2014 Through 12-09-2014",
year = "2014",
month = dec,
day = "1",
doi = "10.1109/JCDL.2014.6970188",
language = "الإنجليزيّة",
series = "Proceedings of the ACM/IEEE Joint Conference on Digital Libraries",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "331--340",
booktitle = "2014 IEEE/ACM Joint Conference on Digital Libraries, JCDL 2014",
address = "الولايات المتّحدة",
}