%0 Conference Paper %1 Klein:2018:FCW:3201064.3201085 %A Klein, Martin %A Balakireva, Lyudmila %A Van de Sompel, Herbert %B Proceedings of the 10th ACM Conference on Web Science %C New York, NY, USA %D 2018 %I ACM %K web %P 333--342 %R 10.1145/3201064.3201085 %T Focused Crawl of Web Archives to Build Event Collections %U http://doi.acm.org/10.1145/3201064.3201085 %X Event collections are frequently built by crawling the live web on the basis of seed URIs nominated by human experts. Focused web crawling is a technique where the crawler is guided by reference content pertaining to the event. Given the dynamic nature of the web and the pace with which topics evolve, the timing of the crawl is a concern for both approaches. We investigate the feasibility of performing focused crawls on the archived web. By utilizing the Memento infrastructure, we obtain resources from 22 web archives that contribute to building event collections. We create collections on four events and compare the relevance of their resources to collections built from crawling the live web as well as from a manually curated collection. Our results show that focused crawling on the archived web can be done and indeed results in highly relevant collections, especially for events that happened further in the past %@ 978-1-4503-5563-6

@inproceedings{Klein:2018:FCW:3201064.3201085, abstract = {Event collections are frequently built by crawling the live web on the basis of seed URIs nominated by human experts. Focused web crawling is a technique where the crawler is guided by reference content pertaining to the event. Given the dynamic nature of the web and the pace with which topics evolve, the timing of the crawl is a concern for both approaches. We investigate the feasibility of performing focused crawls on the archived web. By utilizing the Memento infrastructure, we obtain resources from 22 web archives that contribute to building event collections. We create collections on four events and compare the relevance of their resources to collections built from crawling the live web as well as from a manually curated collection. Our results show that focused crawling on the archived web can be done and indeed results in highly relevant collections, especially for events that happened further in the past}, acmid = {3201085}, added-at = {2023-06-09T10:41:38.000+0200}, address = {New York, NY, USA}, author = {Klein, Martin and Balakireva, Lyudmila and Van de Sompel, Herbert}, biburl = {https://www.bibsonomy.org/bibtex/2a200d0ad88302467e941558f7c290dc3/tobias.koopmann}, booktitle = {Proceedings of the 10th ACM Conference on Web Science}, doi = {10.1145/3201064.3201085}, interhash = {ebb12d3a339288cdc91c5a94202b51fb}, intrahash = {a200d0ad88302467e941558f7c290dc3}, isbn = {978-1-4503-5563-6}, keywords = {web}, location = {Amsterdam, Netherlands}, numpages = {10}, pages = {333--342}, publisher = {ACM}, series = {WebSci '18}, timestamp = {2023-06-09T10:43:50.000+0200}, title = {Focused Crawl of Web Archives to Build Event Collections}, url = {http://doi.acm.org/10.1145/3201064.3201085}, year = 2018 }