{"id":"https://openalex.org/W1482288948","doi":"https://doi.org/10.3233/wia-2012-0232","title":"Selecting queries from sample to crawl deep web data sources","display_name":"Selecting queries from sample to crawl deep web data sources","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W1482288948","doi":"https://doi.org/10.3233/wia-2012-0232","mag":"1482288948"},"language":"en","primary_location":{"id":"doi:10.3233/wia-2012-0232","is_oa":false,"landing_page_url":"https://doi.org/10.3233/wia-2012-0232","pdf_url":null,"source":{"id":"https://openalex.org/S152598483","display_name":"Web Intelligence and Agent Systems An International Journal","issn_l":"1570-1263","issn":["1570-1263","1875-9289"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Web Intelligence and Agent Systems: An International Journal","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100322854","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-9876-5823"},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":["School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca","School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca","institution_ids":["https://openalex.org/I74413500"]},{"raw_affiliation_string":"School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca#TAB#","institution_ids":["https://openalex.org/I74413500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102797606","display_name":"Jianguo L\u00fc","orcid":"https://orcid.org/0000-0003-1042-8847"},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Jianguo Lu","raw_affiliation_strings":["School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca","State Key Lab for Novel Software Technology, Nanjing University, Nanjing, China","School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca and State Key Lab for Novel Software Technology, Nanjing University, Na ...#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca","institution_ids":["https://openalex.org/I74413500"]},{"raw_affiliation_string":"State Key Lab for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca and State Key Lab for Novel Software Technology, Nanjing University, Na ...#TAB#","institution_ids":["https://openalex.org/I74413500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101784190","display_name":"Jie Liang","orcid":"https://orcid.org/0000-0002-0072-2711"},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jie Liang","raw_affiliation_strings":["School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca","School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca","institution_ids":["https://openalex.org/I74413500"]},{"raw_affiliation_string":"School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca#TAB#","institution_ids":["https://openalex.org/I74413500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775028","display_name":"Jessica Chen","orcid":"https://orcid.org/0000-0003-0415-3701"},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jessica Chen","raw_affiliation_strings":["School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca","School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca","institution_ids":["https://openalex.org/I74413500"]},{"raw_affiliation_string":"School of Computer Science, University of Windsor, Windsor, Ontario, Canada, E-mail: {jlu,wang16c,liangr,xjchen}@uwindsor.ca#TAB#","institution_ids":["https://openalex.org/I74413500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062375227","display_name":"Jiming Liu","orcid":"https://orcid.org/0000-0002-8669-9064"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiming Liu","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong, China, E-mail: jiming@comp.hkbu.edu.hk","Department of Computer Science, Hong Kong Baptist University, Hong Kong, China, E-mail: jiming@comp.hkbu.edu.hk#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, China, E-mail: jiming@comp.hkbu.edu.hk","institution_ids":["https://openalex.org/I141568987"]},{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, China, E-mail: jiming@comp.hkbu.edu.hk#TAB#","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1075,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.95007982,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"10","issue":"1","first_page":"75","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.7666256427764893},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6566197872161865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5908561944961548},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4725843667984009},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4403550326824188},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.1961151361465454}],"concepts":[{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.7666256427764893},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6566197872161865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5908561944961548},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4725843667984009},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4403550326824188},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.1961151361465454},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/wia-2012-0232","is_oa":false,"landing_page_url":"https://doi.org/10.3233/wia-2012-0232","pdf_url":null,"source":{"id":"https://openalex.org/S152598483","display_name":"Web Intelligence and Agent Systems An International Journal","issn_l":"1570-1263","issn":["1570-1263","1875-9289"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Web Intelligence and Agent Systems: An International Journal","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.296.3616","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.296.3616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://davinci.newcs.uwindsor.ca/~jlu/wias.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1493526108","https://openalex.org/W1527781663","https://openalex.org/W1601602846","https://openalex.org/W1601949013","https://openalex.org/W1921703248","https://openalex.org/W1944937980","https://openalex.org/W1973625941","https://openalex.org/W1981959724","https://openalex.org/W1985854646","https://openalex.org/W1986828474","https://openalex.org/W2010221274","https://openalex.org/W2013970953","https://openalex.org/W2022158118","https://openalex.org/W2026289298","https://openalex.org/W2029053609","https://openalex.org/W2041258965","https://openalex.org/W2042676911","https://openalex.org/W2050272710","https://openalex.org/W2059453880","https://openalex.org/W2081948558","https://openalex.org/W2084328880","https://openalex.org/W2094060849","https://openalex.org/W2103224511","https://openalex.org/W2104086170","https://openalex.org/W2107279550","https://openalex.org/W2110034127","https://openalex.org/W2118356300","https://openalex.org/W2119088569","https://openalex.org/W2120642948","https://openalex.org/W2123159709","https://openalex.org/W2125969310","https://openalex.org/W2128941908","https://openalex.org/W2131552526","https://openalex.org/W2131738124","https://openalex.org/W2134150392","https://openalex.org/W2148738951","https://openalex.org/W2155166680","https://openalex.org/W2155569834","https://openalex.org/W2170188121","https://openalex.org/W2321470647","https://openalex.org/W2752885492","https://openalex.org/W3004540582","https://openalex.org/W3145128584"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W3088449018","https://openalex.org/W1551575434","https://openalex.org/W4300526709"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"the":[3,26,39],"problem":[4],"of":[5,19,28,38],"selecting":[6],"queries":[7],"to":[8],"efficiently":[9],"crawl":[10],"a":[11,17],"deep":[12,23],"web":[13,24],"data":[14,30],"source":[15],"using":[16],"set":[18],"sample":[20],"documents.":[21],"Crawling":[22],"is":[25],"process":[27],"collecting":[29],"from":[31],"search":[32],"interfaces":[33],"by":[34],"issuing":[35],"queries.":[36],"One":[37],"major":[40],"challenge":[41]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}