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 Demidova2021
%A Demidova, Elena
%A Risse, Thomas
%B The Past Web: Exploring Web Archives
%C Cham
%D 2021
%E Gomes, Daniel
%E Demidova, Elena
%E Winters, Jane
%E Risse, Thomas
%I Springer International Publishing
%K collections events myown webarchiving
%P 57--67
%R 10.1007/978-3-030-63291-5_6
%T Creating Event-Centric Collections from Web Archives
%U https://doi.org/10.1007/978-3-030-63291-5_6
%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.
%@ 978-3-030-63291-5
@inbook{Demidova2021,
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 = {2021-11-25T15:43:47.000+0100},
address = {Cham},
author = {Demidova, Elena and Risse, Thomas},
biburl = {https://www.bibsonomy.org/bibtex/2cc8857ae65ae645f9076532f64f94a0b/trisse69},
booktitle = {The Past Web: Exploring Web Archives},
doi = {10.1007/978-3-030-63291-5_6},
editor = {Gomes, Daniel and Demidova, Elena and Winters, Jane and Risse, Thomas},
interhash = {f2b372bb6117e9e3a3d8fbc0a0854cae},
intrahash = {cc8857ae65ae645f9076532f64f94a0b},
isbn = {978-3-030-63291-5},
keywords = {collections events myown webarchiving},
pages = {57--67},
publisher = {Springer International Publishing},
timestamp = {2022-04-14T14:47:22.000+0200},
title = {Creating Event-Centric Collections from Web Archives},
type = {Publication},
url = {https://doi.org/10.1007/978-3-030-63291-5_6},
year = 2021
}