{"id":"https://openalex.org/W2026989907","doi":"https://doi.org/10.1109/iri.2012.6303014","title":"Discovery and cataloging of deep Web sources","display_name":"Discovery and cataloging of deep Web sources","publication_year":2012,"publication_date":"2012-08-01","ids":{"openalex":"https://openalex.org/W2026989907","doi":"https://doi.org/10.1109/iri.2012.6303014","mag":"2026989907"},"language":"en","primary_location":{"id":"doi:10.1109/iri.2012.6303014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2012.6303014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 13th International Conference on Information Reuse &amp; Integration (IRI)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5083551049","display_name":"Chelsea Hicks","orcid":null},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chelsea Hicks","raw_affiliation_strings":["Department of Computer Science, Texas State University, San Marcos, San Marcos, USA","Department of Computer Science , Texas State University , San Marcos , TX , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Texas State University, San Marcos, San Marcos, USA","institution_ids":["https://openalex.org/I13511017"]},{"raw_affiliation_string":"Department of Computer Science , Texas State University , San Marcos , TX , USA","institution_ids":["https://openalex.org/I13511017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111690147","display_name":"Matthew Scheffer","orcid":null},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Scheffer","raw_affiliation_strings":["Department of Computer Science, Texas State University, San Marcos, San Marcos, USA","Department of Computer Science , Texas State University , San Marcos , TX , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Texas State University, San Marcos, San Marcos, USA","institution_ids":["https://openalex.org/I13511017"]},{"raw_affiliation_string":"Department of Computer Science , Texas State University , San Marcos , TX , USA","institution_ids":["https://openalex.org/I13511017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016020974","display_name":"Anne H. H. Ngu","orcid":"https://orcid.org/0000-0002-5877-0230"},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anne H.H. Ngu","raw_affiliation_strings":["Department of Computer Science, Texas State University, San Marcos, San Marcos, USA","Department of Computer Science , Texas State University , San Marcos , TX , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Texas State University, San Marcos, San Marcos, USA","institution_ids":["https://openalex.org/I13511017"]},{"raw_affiliation_string":"Department of Computer Science , Texas State University , San Marcos , TX , USA","institution_ids":["https://openalex.org/I13511017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080744092","display_name":"Quan Z. Sheng","orcid":"https://orcid.org/0000-0002-3326-4147"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Quan Z. Sheng","raw_affiliation_strings":["Department of Computer science, University of Adelaide, Adelaide, Australia","[Department Of Computer Science, University of Adelaide, Adelaide, SA, Australia]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer science, University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"[Department Of Computer Science, University of Adelaide, Adelaide, SA, Australia]","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4414,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81779112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"224","last_page":"230"},"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/T13976","display_name":"Web visibility and informetrics","score":0.9743000268936157,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9603000283241272,"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/computer-science","display_name":"Computer science","score":0.7644575834274292},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.7107308506965637},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6460222005844116},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.6164673566818237},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5599222779273987},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5354046821594238},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5274995565414429},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.5052981972694397},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5019688606262207},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4915209710597992},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.4914652109146118},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4773571491241455},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.466562420129776},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46461546421051025},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.4486362338066101},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.4278346300125122},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4144912362098694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18217304348945618},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.121042400598526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644575834274292},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.7107308506965637},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6460222005844116},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.6164673566818237},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5599222779273987},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5354046821594238},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5274995565414429},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.5052981972694397},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5019688606262207},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4915209710597992},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.4914652109146118},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4773571491241455},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.466562420129776},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46461546421051025},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.4486362338066101},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.4278346300125122},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4144912362098694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18217304348945618},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.121042400598526},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iri.2012.6303014","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2012.6303014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 13th International Conference on Information Reuse &amp; Integration (IRI)","raw_type":"proceedings-article"},{"id":"pmh:oai:digital.library.adelaide.edu.au:2440/77194","is_oa":false,"landing_page_url":"http://hdl.handle.net/2440/77194","pdf_url":null,"source":{"id":"https://openalex.org/S4306401835","display_name":"Adelaide Research & Scholarship (AR&S) (University of Adelaide)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5681781","host_organization_name":"The University of Adelaide","host_organization_lineage":["https://openalex.org/I5681781"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dx.doi.org/10.1109/iri.2012.6303014","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310830","display_name":"Texas State University","ror":"https://ror.org/009ey6w22"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W343945789","https://openalex.org/W1486989746","https://openalex.org/W1590644098","https://openalex.org/W1969831559","https://openalex.org/W1982047300","https://openalex.org/W1997868819","https://openalex.org/W2013970953","https://openalex.org/W2032973786","https://openalex.org/W2044515729","https://openalex.org/W2098035424","https://openalex.org/W2110034127","https://openalex.org/W2131552526","https://openalex.org/W2131723113","https://openalex.org/W2135343814","https://openalex.org/W2151007976","https://openalex.org/W6611560470","https://openalex.org/W6629100428"],"related_works":["https://openalex.org/W2165396088","https://openalex.org/W2367709753","https://openalex.org/W2392726065","https://openalex.org/W1498286998","https://openalex.org/W2350381501","https://openalex.org/W2390587322","https://openalex.org/W2423684479","https://openalex.org/W2245375266","https://openalex.org/W2120284761","https://openalex.org/W1982433408"],"abstract_inverted_index":{"With":[0],"more":[1,3,73],"and":[2,8,36,50,102],"information":[4,11,23,40,57],"goes":[5],"online,":[6],"extracting":[7],"managing":[9],"the":[10,13,20,39,42,60,65,68],"from":[12,41],"Internet":[14],"is":[15,24,45],"becoming":[16],"increasingly":[17],"important.":[18],"While":[19],"surface":[21,66],"Web's":[22],"relatively":[25],"easy":[26],"to":[27,30,64],"obtain":[28],"thanks":[29],"search":[31,52,80],"engines":[32,53],"such":[33],"as":[34],"Google":[35],"Bing,":[37],"collecting":[38],"deep":[43,61,69,85,110],"Web":[44,70,86,111],"still":[46],"a":[47,78,91,108],"challenging":[48],"task":[49],"these":[51,100],"do":[54],"not":[55],"index":[56,84],"located":[58],"inside":[59],"Web.":[62],"Compared":[63],"Web,":[67],"contains":[71],"vast":[72],"information.":[74],"In":[75,95],"particular,":[76],"building":[77],"generalized":[79,109],"engine":[81],"that":[82,114],"can":[83,115],"across":[87],"all":[88],"domains":[89],"remains":[90],"difficult":[92],"research":[93],"problem.":[94],"this":[96],"paper,":[97],"we":[98],"highlight":[99],"challenges":[101],"demonstrate":[103],"via":[104],"prototype":[105],"implementation":[106],"of":[107],"discovery":[112],"framework":[113],"achieve":[116],"high":[117],"precision.":[118]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
