{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T04:11:26Z","timestamp":1749615086633,"version":"3.41.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,9,3]],"date-time":"2016-09-03T00:00:00Z","timestamp":1472860800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61440020"],"award-info":[{"award-number":["61440020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2014-04463"],"award-info":[{"award-number":["RGPIN-2014-04463"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2017,1]]},"DOI":"10.1007\/s11280-016-0410-4","type":"journal-article","created":{"date-parts":[[2016,9,3]],"date-time":"2016-09-03T05:52:46Z","timestamp":1472881966000},"page":"89-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Crawling ranked deep Web data sources"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9876-5823","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianguo","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jessica","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaxin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,3]]},"reference":[{"key":"410_CR1","doi-asserted-by":"crossref","unstructured":"Alvarez, M., Raposo.Raposo, J., Pan, A., Cacheda, F., Bellas, O., Carneiro, V.: Crawling the Content Hidden behind Web Forms. In: ICCSA, pp 322\u2013333 (2007)","DOI":"10.1007\/978-3-540-74477-1_31"},{"key":"410_CR2","doi-asserted-by":"crossref","unstructured":"Barbosa, L., Freire, J.: An Adaptive Crawler for Locating Hidden-Web Entry Points. In: Proceedings of WWW, pp 441\u2013450 (2007)","DOI":"10.1145\/1242572.1242632"},{"key":"410_CR3","unstructured":"Barbosa, M.L., Freire, J.: Siphoning Hidden-Web Data through Keyword-Based Interfaces. In: Proceedings of SBBD (2004)"},{"key":"410_CR4","doi-asserted-by":"crossref","unstructured":"Bar-Yossef, Z., Gurevich, M.: Random Sampling from a Search Engine\u2019s Index. In: WWW, pp 367\u2013376 (2006)","DOI":"10.1145\/1135777.1135833"},{"key":"410_CR5","doi-asserted-by":"crossref","unstructured":"Bergman, M.K.: The deepWeb: Surfacing hidden value. J. Electron. Publ. 7(1) (2001)","DOI":"10.3998\/3336451.0007.104"},{"key":"410_CR6","doi-asserted-by":"crossref","unstructured":"Dong, X.L., Srivastava, D.: Big Data Integration. In: ICDE, pp 1245\u20131248 (2013)","DOI":"10.1109\/ICDE.2013.6544914"},{"issue":"3","key":"410_CR7","first-page":"973","volume":"8","author":"Y Dong","year":"2012","unstructured":"Dong, Y., Li, Q.: A deep Web crawling approach based on query harvest model. J. Comput. Inf. Syst. 8(3), 973\u2013981 (2012)","journal-title":"J. Comput. Inf. Syst."},{"issue":"5","key":"410_CR8","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1007\/s00778-013-0323-0","volume":"22","author":"T Furche","year":"2013","unstructured":"Furche, T., Gottlob, G., Grasso, G., Guo, X., Orsi, G., Schallhart, C.: The ontological key: automatically understanding and integrating forms to access the deep Web. VLDB J. 22(5), 615\u2013640 (2013)","journal-title":"VLDB J."},{"key":"410_CR9","doi-asserted-by":"crossref","unstructured":"Gale, W.A., Sampson, G.: Good-turing frequency estimation without tears*. Journal of Quantitative Linguistics (1995)","DOI":"10.1080\/09296179508590051"},{"key":"410_CR10","unstructured":"Hatcher, E., Gospodnetic, O.: Lucene in action manning publications (2004)"},{"issue":"5","key":"410_CR11","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1145\/1230819.1241670","volume":"50","author":"B He","year":"2007","unstructured":"He, B., Patel, M., Zhang, Z., Chang, K.C.C.: Accessing the deep Web: a survey. Commun. ACM 50(5), 94\u2013101 (2007)","journal-title":"Commun. ACM"},{"key":"410_CR12","doi-asserted-by":"crossref","unstructured":"He, Y., Xin, D., Ganti, V., Rajaraman, S., Shah, N.: Crawling Deep Web Entity Pages. In: Proceedings of WSDM\u201913, pp 355\u2013364 (2013)","DOI":"10.1145\/2433396.2433442"},{"key":"410_CR13","doi-asserted-by":"crossref","unstructured":"Ipeirotis, P.G., Gravano, L.: Distributed Search over the Hidden Web: Hierarchical Database Sampling and Selection. In: VLDB (2002)","DOI":"10.1016\/B978-155860869-6\/50042-1"},{"key":"410_CR14","doi-asserted-by":"crossref","unstructured":"Jiang, L., Wu, Z., Feng, Q., Liu, J., Zheng, Q.: Efficient Deep Web Crawling Using Reinforcement Learning. In: Proceedings of PAKDD, pp 428\u2013439 (2010)","DOI":"10.1007\/978-3-642-13657-3_46"},{"key":"410_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, L., Wu, Z., Zheng, Q., Liu, J.: Learning Deep Web Crawling with Diverse Featueres. In: WI-IAT, pp 72\u2013575 (2009)","DOI":"10.1109\/WI-IAT.2009.96"},{"issue":"1","key":"410_CR16","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1145\/1860702.1860708","volume":"39","author":"R Khare","year":"2010","unstructured":"Khare, R., An, Y., Song, I.: Understanding deep Web search interfaces: a survey. ACM SIGMOD Rec. 39(1), 33\u201340 (2010)","journal-title":"ACM SIGMOD Rec."},{"key":"410_CR17","unstructured":"Kushmerick, N., Weld, D.S., Doorenbos, R.: Wrapper induction for information extraction. In: Proceedings of IJCAI (97)"},{"key":"410_CR18","first-page":"1","volume":"2015","author":"P Liakos","year":"2015","unstructured":"Liakos, P., Ntoulas, A., A, L., Delis, A.: Focused crawling for the hidden Web. World Wide Web 2015, 1\u201327 (2015)","journal-title":"World Wide Web"},{"key":"410_CR19","doi-asserted-by":"crossref","unstructured":"Liddle, S.W., Embley, D.W., Scott, D.T., Yau, S.H.: Extracting Data behind Web Forms. In: Proceedings of Advanced Conceptual Modeling Techniques (2002)","DOI":"10.1007\/978-3-540-45275-1_35"},{"key":"410_CR20","unstructured":"Liu, J., Wu, Z.H., Jiang, L., Zheng, Q.H., Liu, X.: Crawling Deep Web Content through Query Forms. In: Proceedings of WebIST, 634\u2013642. Lisbon Portugal (2009)"},{"issue":"3","key":"410_CR21","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/TKDE.2009.109","volume":"22","author":"W Liu","year":"2010","unstructured":"Liu, W., Meng, X., Meng, W.: Vide: A vision-based approach for deep Web data extraction. IEEE Trans. Knowl. Data Eng. 22(3), 447\u2013460 (2010)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"8","key":"410_CR22","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1016\/j.datak.2010.03.007","volume":"69","author":"J Lu","year":"2010","unstructured":"Lu, J.: Ranking bias in deep Web size estimation using capture recapture method. J. Data Knowl. Eng. 69(8), 866\u2013879 (2010)","journal-title":"J. Data Knowl. Eng."},{"issue":"1","key":"410_CR23","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1007\/s10791-009-9107-y","volume":"13","author":"J Lu","year":"2010","unstructured":"Lu, J., Li, D.: Estimating deep Web data source size by capture-recapture method. Inf. Retr. 13(1), 70\u201395 (2010)","journal-title":"Inf. Retr."},{"key":"410_CR24","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 Web Intelligence, pp 718\u2013724 (2008)","DOI":"10.1109\/WIIAT.2008.392"},{"key":"410_CR25","unstructured":"Madhavan, J., Afanasiev, L., Antova, L., Halevy, A.: Harnessing the Deep Web: Present and Future. In: Proceedings of CIDR (2009)"},{"key":"410_CR26","doi-asserted-by":"crossref","unstructured":"Madhavan, J., Ko, D., Kot, \u0141., Ganapathy, V., Rasmussen, A., Halevy, A.: Google\u2019S Deep-Web Crawl. In: Proceedings of VLDB, pp 1241\u20131252 (2008)","DOI":"10.14778\/1454159.1454163"},{"key":"410_CR27","unstructured":"Mandelbrot, B.B.: Fractal Geometry of Nature. W.H. Freeman Press (1988)"},{"issue":"8","key":"410_CR28","doi-asserted-by":"crossref","first-page":"1830","DOI":"10.1109\/TKDE.2012.111","volume":"25","author":"MC Moraes","year":"2013","unstructured":"Moraes, M.C., Heuser, C.A., Moreira, V.P., Barbosa, D.: Prequery discovery of domain-specific query forms: a survey. Knowledge and data engineering. IEEE Trans. Knowl. Data Eng. 25(8), 1830\u20131848 (2013)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"410_CR29","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/S0022-2496(02)00028-7","volume":"47","author":"IJ Myung","year":"2003","unstructured":"Myung, I.J.: Tutorial on maximum likelihood estimation. J. Math. Psychol. 47, 90\u2013100 (2003)","journal-title":"J. Math. Psychol."},{"key":"410_CR30","doi-asserted-by":"crossref","unstructured":"Peng, M., Zhu, J., Li, X., Huang, J., Wang, H., Zhang, Y.: Central Topic Model for Event-Oriented Topics Mining in Microblog Stream. In: Proceedings of CIKM, pp 1611\u20131620 (2015)","DOI":"10.1145\/2806416.2806561"},{"key":"410_CR31","unstructured":"Raghavan, S., Garcia-Molina, H.: Crawling the Hidden Web. In: Proceedings of the 27Th International Conference on Very Large Data Bases (VLDB), pp 129\u2013138 (2001)"},{"issue":"3","key":"410_CR32","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/S0169-023X(04)00107-7","volume":"52","author":"D Shestakov","year":"2005","unstructured":"Shestakov, D., Bhowmick, S.S., Lim, E.P.: Deque: querying the deep Web. J. Data Knowl. Eng. 52(3), 273\u2013311 (2005)","journal-title":"J. Data Knowl. Eng."},{"issue":"2","key":"410_CR33","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/s11280-012-0163-7","volume":"16","author":"S Song","year":"2013","unstructured":"Song, S., Chen, L.: Indexing dataspaces with partitions. World Wide Web 16 (2), 141\u2013170 (2013)","journal-title":"World Wide Web"},{"key":"410_CR34","unstructured":"Valkanas, G., Ntoulas, A., Gunopulos, D.: Rank-Aware Crawling of Hidden Web Sites. In: Proceedings of in WebDB (2011)"},{"key":"410_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, H., Wang, H., Zhou, B., Zhang, Y.: Multi-Window Based Ensemble Learning for Classification of Imbalanced Streaming Data. In: Proceedings of WISE, pp 78\u201392 (2015)","DOI":"10.1007\/978-3-319-26187-4_6"},{"key":"410_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, Y., Pi, N., Lu, J.: Crawling Ranked Deep Web Data Sources. In: Proceedings of WISE, pp 384\u2013398 (2015)","DOI":"10.1007\/978-3-319-26190-4_26"},{"issue":"3","key":"410_CR37","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1007\/s10791-013-9230-7","volume":"17","author":"Y Wang","year":"2014","unstructured":"Wang, Y., Liang, J., Lu, J.: Discover hidden Web properties by random walk on bipartite graph. Inf. Retr. 17(3), 203\u2013228 (2014)","journal-title":"Inf. Retr."},{"key":"410_CR38","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lu, J., Chen, J.: Crawling Deep Web Using a New Set Covering Algorithm. In: Proceedings of ADMA, pp 326\u2013337 (2009)","DOI":"10.1007\/978-3-642-03348-3_32"},{"key":"410_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Lu, J., Chen, J.: Ts-Ids Algorithm for Query Selection in the Deep Web Crawling. In: ApWeb, pp 189\u2013200 (2014)","DOI":"10.1007\/978-3-319-11116-2_17"},{"issue":"1","key":"410_CR40","doi-asserted-by":"crossref","first-page":"75","DOI":"10.3233\/WIA-2012-0232","volume":"10","author":"Y Wang","year":"2012","unstructured":"Wang, Y., Lu, J., Liang, J., Chen, J., Liu, J.: Selecting queries from sample to crawl deep Web data sources. Web Intelligence Agent Syst. 10(1), 75\u201388 (2012)","journal-title":"Web Intelligence Agent Syst."},{"issue":"2","key":"410_CR41","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/s10618-007-0065-y","volume":"15","author":"L Wen","year":"2007","unstructured":"Wen, L., van der Aalst, W.M., Wang, J., Sun, J.: Mining process models with non-free-choice constructs. Data Min. Knowl. Disc. 15(2), 145\u2013180 (2007)","journal-title":"Data Min. Knowl. Disc."},{"key":"410_CR42","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. In: Proceedings of ICDE, pp 47\u201356 (2006)","DOI":"10.1109\/ICDE.2006.124"},{"key":"410_CR43","doi-asserted-by":"crossref","unstructured":"Yang, M., Wang, H.L.L., Wang, M.: Optimizing Content Freshness of Relations Extracted from the Web Using Keyword Search. In: Proceedings of SIGMOND, pp 819\u2013830 (2010)","DOI":"10.1145\/1807167.1807256"},{"key":"410_CR44","doi-asserted-by":"crossref","unstructured":"Zerfos, P., Cho, J., Ntoulas, A.: Downloading Textual Hidden Web Content through Keyword Queries. In: Proceedings of the Joint Conference on Digital Libraries (JCDL), pp 100\u2013109 (2005)","DOI":"10.1145\/1065385.1065407"},{"issue":"6","key":"410_CR45","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1016\/j.is.2013.02.001","volume":"38","author":"Q Zheng","year":"2013","unstructured":"Zheng, Q., Wu, Z., Cheng, X., Jiang, L., Liu, J.: Learning to crawl deep Web. Inf. Syst. 38(6), 801\u2013819 (2013)","journal-title":"Inf. Syst."}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-016-0410-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11280-016-0410-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-016-0410-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-016-0410-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T16:41:41Z","timestamp":1749573701000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11280-016-0410-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,9,3]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,1]]}},"alternative-id":["410"],"URL":"https:\/\/doi.org\/10.1007\/s11280-016-0410-4","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"type":"print","value":"1386-145X"},{"type":"electronic","value":"1573-1413"}],"subject":[],"published":{"date-parts":[[2016,9,3]]}}}