Web archives are an essential information source for research on historical events. However, the large scale and heterogeneity of web archives make it difficult for researchers to access relevant event-specific materials. In this chapter, we discuss methods for creating event-centric collections from large-scale web archives. These methods are manifold and may require manual curation, adopt search or deploy focused crawling. In this chapter, we focus on the crawl-based methods that identify relevant documents in and across web archives and include link networks as context in the resulting collections.
%0 Book Section
%1 demidova2021creating
%A Demidova, Elena
%A Risse, Thomas
%B The past Web
%D 2021
%I Springer
%K myown
%P 57-67
%R https://doi.org/10.1007/978-3-030-63291-5_6
%T Creating Event-Centric Collections from Web Archives
%X Web archives are an essential information source for research on historical events. However, the large scale and heterogeneity of web archives make it difficult for researchers to access relevant event-specific materials. In this chapter, we discuss methods for creating event-centric collections from large-scale web archives. These methods are manifold and may require manual curation, adopt search or deploy focused crawling. In this chapter, we focus on the crawl-based methods that identify relevant documents in and across web archives and include link networks as context in the resulting collections.
%& https://link.springer.com/chapter/10.1007/978-3-030-63291-5_6
@incollection{demidova2021creating,
abstract = {Web archives are an essential information source for research on historical events. However, the large scale and heterogeneity of web archives make it difficult for researchers to access relevant event-specific materials. In this chapter, we discuss methods for creating event-centric collections from large-scale web archives. These methods are manifold and may require manual curation, adopt search or deploy focused crawling. In this chapter, we focus on the crawl-based methods that identify relevant documents in and across web archives and include link networks as context in the resulting collections.},
added-at = {2021-07-31T20:25:02.000+0200},
author = {Demidova, Elena and Risse, Thomas},
biburl = {https://www.bibsonomy.org/bibtex/23e9ccad289366c181af470868c58c7fb/demidova},
booktitle = {The past Web},
chapter = {https://link.springer.com/chapter/10.1007/978-3-030-63291-5_6},
doi = {https://doi.org/10.1007/978-3-030-63291-5_6},
interhash = {f2b372bb6117e9e3a3d8fbc0a0854cae},
intrahash = {3e9ccad289366c181af470868c58c7fb},
keywords = {myown},
pages = {57-67},
publisher = {Springer},
timestamp = {2022-02-27T13:57:23.000+0100},
title = {Creating Event-Centric Collections from Web Archives},
year = 2021
}