{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T13:36:51Z","timestamp":1761917811697,"version":"3.41.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2015,5,21]],"date-time":"2015-05-21T00:00:00Z","timestamp":1432166400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2016,7]]},"DOI":"10.1007\/s11280-015-0349-x","type":"journal-article","created":{"date-parts":[[2015,5,20]],"date-time":"2015-05-20T05:42:23Z","timestamp":1432100543000},"page":"605-631","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Focused crawling for the hidden web"],"prefix":"10.1007","volume":"19","author":[{"given":"Panagiotis","family":"Liakos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandros","family":"Ntoulas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandros","family":"Labrinidis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Delis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,5,21]]},"reference":[{"key":"349_CR1","doi-asserted-by":"crossref","unstructured":"\u00c1lvarez, M., Raposo, J., Pan, A., Cacheda, F., Bellas, F., Carneiro, V.: Deepbot: A focused crawler for accessing hidden web content. In: Proceedings of the 3rd International Workshop on Data Enginering Issues in E-commerce and Services (EC), pp. 18\u201325, San Diego (2007)","DOI":"10.1145\/1278380.1278385"},{"key":"349_CR2","unstructured":"Barbosa, L., Freire, J.: Siphoning hidden-web data through keyword-based interfaces. In: SBBD, pp. 309\u2013321. Distrito Federal, Brasil (2004)"},{"key":"349_CR3","unstructured":"Barbosa, L., Freire, J.: Searching for hidden-web databases. In: Proceedings of the 8th International WebDB, pp. 1\u20136, Baltimore (2005)"},{"key":"349_CR4","doi-asserted-by":"crossref","unstructured":"Barbosa, L., Freire, J.: An adaptive crawler for locating hidden-web entry points. In: Proceedings of the 16th International Conference on World Wide Web (WWW), pp. 441\u2013450. Banff, Canada (2007)","DOI":"10.1145\/1242572.1242632"},{"key":"349_CR5","doi-asserted-by":"crossref","unstructured":"Bergholz, A., Chidlovskii, B.: Crawling for domain-specific hidden web resources. In: Proceedings of the 4th International Conference on Web Information Systems Engineering (WISE), pp. 125\u2013133, Roma (2003)","DOI":"10.1109\/WISE.2003.1254476"},{"issue":"1","key":"349_CR6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3998\/3336451.0007.104","volume":"7","author":"MK Bergman","year":"2001","unstructured":"Bergman, M.K.: The deep web. surfacing hidden value. J. Electron. Publ. 7(1), 1\u201317 (2001)","journal-title":"J. Electron. Publ."},{"issue":"4","key":"349_CR7","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1145\/1519103.1519112","volume":"37","author":"MJ Cafarella","year":"2009","unstructured":"Cafarella, M.J., Madhavan, J., Halevy, A.: Web-scale extraction of structured data. SIGMOD Rec. 37(4), 55\u201361 (2009)","journal-title":"SIGMOD Rec."},{"key":"349_CR8","doi-asserted-by":"crossref","unstructured":"Chakrabarti, S., van den Berg, M., Dom, B.: Focused crawling: A new approach to topic-specific web resource discovery. In: In Proceedings of the 8th International Conference on World Wide Web (WWW), pp. 1623\u20131640, Toronto (1999)","DOI":"10.1016\/S1389-1286(99)00052-3"},{"key":"349_CR9","unstructured":"Diligenti, M., Coetzee, F., Lawrence, S., Giles, C.L., Gori, M.: Focused crawling using context graphs. In: Proceedings of the 26th International Conference on Very Large Data Bases (VLDB), pp. 527\u2013534, Cairo (2000)"},{"issue":"2\u20133","key":"349_CR10","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1023\/A:1007465528199","volume":"29","author":"N Friedman","year":"1997","unstructured":"Friedman, N., Geiger, D., Goldszmidt, M.: Bayesian network classifiers. Mach. Learn. 29(2\u20133), 131\u2013163 (1997)","journal-title":"Mach. Learn."},{"issue":"1","key":"349_CR11","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: An update. SIGKDD Explor. Newsl. 11(1), 10\u201318 (2009)","journal-title":"SIGKDD Explor. Newsl."},{"key":"349_CR12","doi-asserted-by":"crossref","unstructured":"He, B., Patel, M., Zhang, Z., Chang, K.C.-C.: Accessing the deep web: A survey. Communications of the ACM 50(5), 94\u2013101 (2007)","DOI":"10.1145\/1230819.1241670"},{"key":"349_CR13","doi-asserted-by":"crossref","unstructured":"Ipeirotis P.G., Gravano, L.: Distributed search over the hidden web: Hierarchical database sampling and selection. In: Proceedings of the 28th International Conference on Very Large Data Bases (VLDB), pp. 394\u2013405, Hong Kong (2002)","DOI":"10.1016\/B978-155860869-6\/50042-1"},{"key":"349_CR14","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1145\/376284.375671","volume":"30","author":"PG Ipeirotis","year":"2001","unstructured":"Ipeirotis, P.G., Gravano, L., Sahami, M.: Probe, count, and classify: Categorizing hidden web databases. SIGMOD Rec. 30, 67\u201378 (2001)","journal-title":"SIGMOD Rec."},{"key":"349_CR15","doi-asserted-by":"crossref","unstructured":"Liakos P., Ntoulas, A.: Topic-sensitive hidden-web crawling. In: Proceedings of the 13th International Conference on Web Information Systems Engineering (WISE), pp. 538\u2013551, Paphos (2012)","DOI":"10.1007\/978-3-642-35063-4_39"},{"issue":"3","key":"349_CR16","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1023\/A:1007608224229","volume":"40","author":"T-S Lim","year":"2000","unstructured":"Lim, T.-S., Loh, W.-Y., Shih, Y.-S.: A comparison of prediction accuracy, complexity, and training time of old, thirty-three algorithms, new classification. Mach. Learn. 40(3), 203\u2013228 (2000)","journal-title":"Mach. Learn."},{"key":"349_CR17","doi-asserted-by":"crossref","unstructured":"Lu, J., Wang, Y., Liang, J., Chen, J., Liu, J.: An approach to deep web crawling by sampling. In: Proceedings of the 2008 IEEE \/ WIC \/ ACM International Conference on Web Intelligence, (WI), pp. 718\u2013724, New SouthWales (2008)","DOI":"10.1109\/WIIAT.2008.392"},{"issue":"2","key":"349_CR18","doi-asserted-by":"crossref","first-page":"1241","DOI":"10.14778\/1454159.1454163","volume":"1","author":"J Madhavan","year":"2008","unstructured":"Madhavan, J., Ko, D., Kot, \u0141., Ganapathy, V., Rasmussen, A., Halevy, A.: Google\u2019s deep web crawl. Proc. VLDB Endow. 1(2), 1241\u20131252 (2008)","journal-title":"Proc. VLDB Endow."},{"key":"349_CR19","volume-title":"Lucene in Action","author":"M McCandless","year":"2010","unstructured":"McCandless, M., Hatcher, E., Gospodnetic, O.: Lucene in Action, 2nd. Manning Publications Co., Greenwich (2010)","edition":"2"},{"key":"349_CR20","doi-asserted-by":"crossref","unstructured":"Noh, S., Choi, Y., Seo, H., Choi, K., Jung, G.: An intelligent topic-specific crawler using degree of relevance. In: IDEAL, volume 3177 of Lecture Notes in Computer Science, pp. 491\u2013498 (2004)","DOI":"10.1007\/978-3-540-28651-6_72"},{"key":"349_CR21","doi-asserted-by":"crossref","unstructured":"Ntoulas, A., Zerfos, P., Cho, J.: Downloading textual hidden web content through keyword queries. In: Proceedings of the 5th ACM\/IEEE-CS Joint Conference on Digital Libraries (JCDL), pp. 100\u2013109, Denver (2005)","DOI":"10.1145\/1065385.1065407"},{"key":"349_CR22","first-page":"185","volume-title":"Advances in Kernel Methods. Chapter Fast Training of Support Vector Machines Using Sequential Minimal Optimization","author":"JC Platt","year":"1999","unstructured":"Platt, J.C.: Advances in Kernel Methods. Chapter Fast Training of Support Vector Machines Using Sequential Minimal Optimization, pp. 185\u2013208. MIT Press, Cambridge (1999)"},{"key":"349_CR23","unstructured":"Raghavan, S., Garcia-Molina, H.: Crawling the hidden web. In: Proceedings of the 27th International Conference on Very Large Data Bases (VLDB), p. 2001, Roma"},{"key":"349_CR24","volume-title":"Introduction to Modern Information Retrieval","author":"G Salton","year":"1986","unstructured":"Salton, G., McGill, M.J.: Introduction to Modern Information Retrieval. McGraw-Hill Inc., New York (1986)"},{"key":"349_CR25","doi-asserted-by":"crossref","unstructured":"Schonhofen, P.: Identifying document topics using the wikipedia category network. In: Proceedings of the 2006 IEEE\/WIC\/ACM International Conference on Web Intelligence (WI), pp. 456\u2013462, Hong Kong (2006)","DOI":"10.1109\/WI.2006.92"},{"key":"349_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lu, J., Chen, J.: Crawling deep web using a new set covering algorithm. In: Proceedings of the 5th International Conference on Advanced Data Mining and Applications (ADMA), pp. 326\u2013337, Beijing (2009)","DOI":"10.1007\/978-3-642-03348-3_32"},{"key":"349_CR27","doi-asserted-by":"crossref","unstructured":"Wu, P., Wen, J.-R., Liu, H., Ma, W.-Y. : Query selection techniques for efficient crawling of structured web sources, p. 47, Atlanta (2006)","DOI":"10.1109\/ICDE.2006.124"},{"key":"349_CR28","doi-asserted-by":"crossref","unstructured":"Wu, W., Yu, C., Doan, A., Meng, W.: An interactive clustering-based approach to integrating source query interfaces on the deep web. In: Proceedings of the 2004 ACM SIGMOD International Conference on Management of Data, pp. 95\u2013106, Paris (2004)","DOI":"10.1145\/1007568.1007582"},{"key":"349_CR29","doi-asserted-by":"crossref","unstructured":"Yang, Y., Bansal, N., Dakka, W., Ipeirotis, P., Koudas, N., Papadias D.: Query by document. In: Proceedings of the 2nd ACM International Conference on Web Search and Data Mining (WSDM), pp. 34\u201343, Barcelona (2009)","DOI":"10.1145\/1498759.1498806"},{"key":"349_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, Z, He, B., Chang, K. C.-C.: Understanding web query interfaces: Best-effort parsing with hidden syntax. In: Proceedings of the 2004 ACM SIGMOD International Conference on Management of Data, pp. 107\u2013118, Paris (2004)","DOI":"10.1145\/1007568.1007583"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-015-0349-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11280-015-0349-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-015-0349-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T01:19:42Z","timestamp":1748395182000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11280-015-0349-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5,21]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2016,7]]}},"alternative-id":["349"],"URL":"https:\/\/doi.org\/10.1007\/s11280-015-0349-x","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"type":"print","value":"1386-145X"},{"type":"electronic","value":"1573-1413"}],"subject":[],"published":{"date-parts":[[2015,5,21]]}}}