{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T02:59:33Z","timestamp":1765421973203,"version":"3.40.3"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319279312"},{"type":"electronic","value":"9783319279329"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/2.5\/"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/2.5\/"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-27932-9_14","type":"book-chapter","created":{"date-parts":[[2016,1,6]],"date-time":"2016-01-06T04:34:33Z","timestamp":1452054873000},"page":"153-166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Semantic URL Analytics to Support Efficient Annotation of Large Scale Web Archives"],"prefix":"10.1007","author":[{"given":"Tarcisio","family":"Souza","sequence":"first","affiliation":[]},{"given":"Elena","family":"Demidova","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Risse","sequence":"additional","affiliation":[]},{"given":"Helge","family":"Holzmann","sequence":"additional","affiliation":[]},{"given":"Gerhard","family":"Gossen","sequence":"additional","affiliation":[]},{"given":"Julian","family":"Szymanski","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,1,7]]},"reference":[{"key":"14_CR1","unstructured":"Abramson, M., Aha, D.: What\u2019s in a URL? genre classification from URLs. In: Proceedings of AAAI workshop on Intelligent Techniques for Web Personalization and Recommender Systems (2012)"},{"key":"14_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1007\/978-3-642-04686-5_49","volume-title":"Progress in Artificial Intelligence","author":"I Anast\u00e1cio","year":"2009","unstructured":"Anast\u00e1cio, I., Martins, B., Calado, P.: Classifying documents according to locational relevance. In: Lopes, L.S., Lau, N., Mariano, P., Rocha, L.M. (eds.) EPIA 2009. LNCS, vol. 5816, pp. 598\u2013609. Springer, Heidelberg (2009)"},{"issue":"1","key":"14_CR3","doi-asserted-by":"publisher","first-page":"176","DOI":"10.14778\/1453856.1453880","volume":"1","author":"E Baykan","year":"2008","unstructured":"Baykan, E., Henzinger, M., Weber, I.: Web page language identification based on URLs. PVLDB Endow. 1(1), 176\u2013187 (2008)","journal-title":"PVLDB Endow."},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Baykan, E., Henzinger, M., Marian, L., Weber, I.: A comprehensive study of features and algorithms for URL-based topic classification. ACM Transactions Web (2011)","DOI":"10.1145\/1993053.1993057"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Baykan, E., Henzinger, M., Weber, I.: A comprehensive study of techniques for URL-based web page language classification. ACM Transactions Web (2013)","DOI":"10.1145\/2435215.2435218"},{"key":"14_CR6","unstructured":"Br\u00fcgger, N.: Probing a nation\u2019s web sphere: a new approach to web history and a new kind of historical source. In Proceedings of the 2014 ACM conference on Web science (2014)"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Craswell, N., Hawking, D., Robertson, S.: Effective site finding using link anchor information. In: Proceedings of the 24th Annual International ACM SIGIR, SIGIR 2001, ACM, New York (2001)","DOI":"10.1145\/383952.383999"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Hern\u00e1ndez, I., Rivero, C.R., Ruiz, D., Corchuelo, R.: A statistical approach to URL-based web page clustering. In: Proceedings of the 21st International Conference Companion on World Wide Web, WWW 2012, ACM, New York (2012)","DOI":"10.1145\/2187980.2188109"},{"key":"14_CR9","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/978-3-642-28795-4_13","volume-title":"Trends in Practical Applications of Agents and Multiagent Systems","author":"I Hern\u00e1ndez","year":"2012","unstructured":"Hern\u00e1ndez, I., Rivero, C.R., Ruiz, D., Arjona, J.L.: An experiment to test URL features for web page classification. In: Rodr\u00edguez, J.M.C., P\u00e9rez, J.B., Golinska, P., Giroux, S., Corchuelo, R. (eds.) Trends in PAAMS. AISC, vol. 157, pp. 109\u2013116. Springer, Heidelberg (2012)"},{"key":"14_CR10","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/j.knosys.2013.12.019","volume":"57","author":"I Hernndez","year":"2014","unstructured":"Hernndez, I., Rivero, C.R., Ruiz, D., Corchuelo, R.: CALA: an unsupervised URL-based web page classification system. Knowl. Based Syst. 57, 168\u2013180 (2014)","journal-title":"Knowl. Based Syst."},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Kan, M.-Y., Thi, H.O.N.: Fast webpage classification using URL features. In: Proceedings of the 14th ACM International Conference on Information and Knowledge Management, CIKM 2005, ACM, New York (2005)","DOI":"10.1145\/1099554.1099649"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Koppula, H.S., Leela, K.P., Agarwal, A., Chitrapura, K.P., Garg, S., Sasturkar, A.: Learning URL patterns for webpage de-duplication. In: Proceedings of the Third ACM International Conference on Web Search and Data Mining, WSDM 2010, New York (2010)","DOI":"10.1145\/1718487.1718535"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Raju, S., Udupa, R.: Extracting advertising keywords from URL strings. In: Proceedings of the 21st International Conference Companion on World Wide Web, WWW 2012, ACM, New York (2012)","DOI":"10.1145\/2187980.2188140"},{"key":"14_CR14","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)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Zhao, P., Hoi, S.C.H.: Cost-sensitive online active learning with application to malicious URL detection. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2013, ACM, New York (2013)","DOI":"10.1145\/2487575.2487647"}],"container-title":["Lecture Notes in Computer Science","Semantic Keyword-Based Search on Structured Data Sources"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-27932-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T19:10:21Z","timestamp":1738091421000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-27932-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319279312","9783319279329"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-27932-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"7 January 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}