@inproceedings{a786ba96079b4831a26ed384d974fc4b,
title = "Uncovering the unarchived web",
abstract = "Many national and international heritage institutes realize the importance of archiving the web for future culture heritage. Web archiving is currently performed either by harvesting a national domain, or by crawling a pre-defined list of websites selected by the archiving institution. In either method, crawling results in more information being harvested than just the websites intended for preservation; which could be used to reconstruct impressions of pages that existed on the live web of the crawl date, but would have been lost forever. We present a method to create representations of what we will refer to as a web collection's aura: the web documents that were not included in the archived collection, but are known to have existed | due to their mentions on pages that were included in the archived web collection. To create representations of these unarchived pages, we exploit the information about the unarchived URLs that can be derived from the crawls by combining crawl date distribution, anchor text and link structure. We illustrate empirically that the size of the aura can be substantial: in 2012, the Dutch Web archive contained 12.3M unique pages, while we uncover references to 11.9M additional (unarchived) pages.",
keywords = "Anchor text, Information retrieval, Web archives, Web archiving, Web crawlers, Web graph",
author = "Thaer Samar and Huurdeman, {Hugo C.} and Anat Ben-David and Jaap Kamps and {De Vries}, Arjen",
year = "2014",
doi = "https://doi.org/10.1145/2600428.2609544",
language = "الإنجليزيّة",
isbn = "9781450322591",
series = "SIGIR 2014 - Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval",
pages = "1199--1202",
booktitle = "SIGIR 2014 - Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval",
note = "37th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2014 ; Conference date: 06-07-2014 Through 11-07-2014",
}