{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T09:23:14Z","timestamp":1770888194562,"version":"3.50.1"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319670072","type":"print"},{"value":"9783319670089","type":"electronic"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-67008-9_10","type":"book-chapter","created":{"date-parts":[[2017,9,1]],"date-time":"2017-09-01T02:46:02Z","timestamp":1504233962000},"page":"116-127","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Extracting Event-Centric Document Collections from Large-Scale Web Archives"],"prefix":"10.1007","author":[{"given":"Gerhard","family":"Gossen","sequence":"first","affiliation":[]},{"given":"Elena","family":"Demidova","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Risse","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,9,2]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Aggarwal, C., Al-Garawi, F., Yu, P.S.: Intelligent crawling on the world wide web with arbitrary predicates. In: World Wide Web Conference, pp. 96\u2013105 (2001)","DOI":"10.1145\/371920.371955"},{"key":"10_CR2","unstructured":"Berberich, K., Bedathur, S.: Temporal diversification of search results. In: Workshop on Time-aware Information Access (TAIA 2013) (2013)"},{"key":"10_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/3-540-45747-X_7","volume-title":"Research and Advanced Technology for Digital Libraries","author":"D Bergmark","year":"2002","unstructured":"Bergmark, D., Lagoze, C., Sbityakov, A.: Focused crawls, tunneling, and digital libraries. In: Agosti, M., Thanos, C. (eds.) ECDL 2002. LNCS, vol. 2458, pp. 91\u2013106. Springer, Heidelberg (2002). doi:10.1007\/3-540-45747-X_7"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Chakrabarti, S., van den Berg, M., Dom, B.: Focused crawling: a new approach to topic-specific web resource discovery. Comput. Netw. 31(11\u201316) (1999)","DOI":"10.1016\/S1389-1286(99)00052-3"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Costa, M., Couto, F., Silva, M.: Learning temporal-dependent ranking models. In: SIGIR 2014 (2014)","DOI":"10.1145\/2600428.2609619"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Costa, M., Gomes, D., Silva, M.J.: The evolution of web archiving. IJDL (2016)","DOI":"10.1007\/s00799-016-0171-9"},{"key":"10_CR7","unstructured":"Diligenti, M., Coetzee, F., Lawrence, S., Giles, C.L., Gori, M.: Focused crawling using context graphs. In: VLDB (2000)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Dong, A., Chang, Y., Zheng, Z., Mishne, G., Bai, J., Zhang, R., Buchner, K., Liao, C., Diaz, F.: Towards recency ranking in web search. In: WSDM 2010 (2010)","DOI":"10.1145\/1718487.1718490"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Dong, H., Hussain, F.K.: SOF: a semi-supervised ontology-learning-based focused crawler. Concurrency Computat. Prac. Experience 25(12) (2013)","DOI":"10.1002\/cpe.2980"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Ehrig, M., Maedche, A.: Ontology-focused crawling of web documents. In: ACM SAC (2003)","DOI":"10.1145\/952532.952761"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Farag, M.M.G., Lee, S., Fox, E.A.: Focused crawler for events. IJDL (2017)","DOI":"10.1007\/s00799-016-0207-1"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Gossen, G., Demidova, E., Risse, T.: iCrawl: Improving the freshness of web collections by integrating social web and focused web crawling. In: JCDL 2015 (2015)","DOI":"10.1145\/2756406.2756925"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Gossen, G., Demidova, E., Risse, T.: The iCrawl Wizard \u2013 supporting interactive focused crawl specification. In: ECIR 2015 (2015)","DOI":"10.1007\/978-3-319-16354-3_88"},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Gossen, G., Demidova, E., Risse, T.: Analyzing web archives through topic and event focused sub-collections. In: WebSci 2016. pp. 291\u2013295, May 2016","DOI":"10.1145\/2908131.2908175"},{"issue":"4","key":"10_CR15","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1023\/A:1019213109274","volume":"2","author":"A Heydon","year":"1999","unstructured":"Heydon, A., Najork, M.: Mercator: a scalable, extensible web crawler. World Wide Web 2(4), 219\u2013229 (1999)","journal-title":"World Wide Web"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Jackson, A., Lin, J., Milligan, I., Ruest, N.: Desiderata for exploratory search interfaces to web archives in support of scholarly activities. In: JCDL2016 (2016)","DOI":"10.1145\/2910896.2910912"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, J., Song, X., Yu, N., Lin, C.Y.: Focus: Learning to crawl web forums. IEEE TKDE 25(6) (2013)","DOI":"10.1109\/TKDE.2012.56"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Kanhabua, N., N\u00f8rv\u00e5g, K.: A comparison of time-aware ranking methods. In: SIGIR 2011 (2011)","DOI":"10.1145\/2009916.2010147"},{"key":"10_CR19","unstructured":"Laranjeira, B., Moreira, V., Villavicencio, A., Ramisch, C., Finatto, M.J.: Comparing the quality of focused crawlers and of the translation resources obtained from them. In: LREC 2014 (2014)"},{"key":"10_CR20","unstructured":"Mohr, G., Kimpton, M., Stack, M., Ranitovic, I.: Introduction to Heritrix, an archival quality web crawler. In: 4th International Web Archiving Workshop (2004)"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Nguyen, T.N., Kanhabua, N., Nieder\u00e9e, C., Zhu, X.: A time-aware random walk model for finding important documents in web archives. In: SIGIR 2015 (2015)","DOI":"10.1145\/2766462.2767832"},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Pant, G., Srinivasan, P.: Learning to crawl: Comparing classification schemes. ACM Trans. Inf. Syst. 23(4) (2005)","DOI":"10.1145\/1095872.1095875"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Pant, G., Srinivasan, P., Menczer, F.: Crawling the web. In: Web Dynamics (2004)","DOI":"10.1007\/978-3-662-10874-1_7"},{"key":"10_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1007\/978-3-319-06028-6_53","volume-title":"Advances in Information Retrieval","author":"P Pereira","year":"2014","unstructured":"Pereira, P., Macedo, J., Craveiro, O., Madeira, H.: Time-aware focused web crawling. In: Rijke, M., Kenter, T., Vries, A.P., Zhai, C.X., Jong, F., Radinsky, K., Hofmann, K. (eds.) ECIR 2014. LNCS, vol. 8416, pp. 534\u2013539. Springer, Cham (2014). doi:10.1007\/978-3-319-06028-6_53"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Qin, J., Zhou, Y., Chau, M.: Building domain-specific web collections for scientific digital libraries. In: JCDL 2004 (2004)","DOI":"10.1145\/996350.996383"},{"key":"10_CR26","unstructured":"Risse, T., Demidova, E., Gossen, G.: What do you want to collect from the web? In: Proceedings of the Building Web Observatories Workshop (BWOW) 2014 (2014)"}],"container-title":["Lecture Notes in Computer Science","Research and Advanced Technology for Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-67008-9_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:45:21Z","timestamp":1710333921000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-67008-9_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319670072","9783319670089"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-67008-9_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"2 September 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}