{"id":"https://openalex.org/W2763509600","doi":"https://doi.org/10.1093/comjnl/bxx098","title":"Structural analysis and classification of search interfaces for the deep web","display_name":"Structural analysis and classification of search interfaces for the deep web","publication_year":2017,"publication_date":"2017-10-08","ids":{"openalex":"https://openalex.org/W2763509600","doi":"https://doi.org/10.1093/comjnl/bxx098","mag":"2763509600"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxx098","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxx098","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer 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/A5024971243","display_name":"Vasilis Kolias","orcid":null},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vasilis Kolias","raw_affiliation_strings":["University of Thessaly, Papassiopoulou 2-4. 35100, Galaneika, Lamia, Greece"],"affiliations":[{"raw_affiliation_string":"University of Thessaly, Papassiopoulou 2-4. 35100, Galaneika, Lamia, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045528384","display_name":"Ioannis Anagnostopoulos","orcid":"https://orcid.org/0000-0002-0832-0522"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Ioannis Anagnostopoulos","raw_affiliation_strings":["University of Thessaly, Papassiopoulou 2-4. 35100, Galaneika, Lamia, Greece"],"affiliations":[{"raw_affiliation_string":"University of Thessaly, Papassiopoulou 2-4. 35100, Galaneika, Lamia, Greece","institution_ids":["https://openalex.org/I145722265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002810652","display_name":"Sherali Zeadally","orcid":"https://orcid.org/0000-0002-5982-8190"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sherali Zeadally","raw_affiliation_strings":["University of Kentucky, 315 Little Library Building, College of Communication and Information, Lexington, KY 40506-0224, USA"],"affiliations":[{"raw_affiliation_string":"University of Kentucky, 315 Little Library Building, College of Communication and Information, Lexington, KY 40506-0224, USA","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045528384"],"corresponding_institution_ids":["https://openalex.org/I145722265"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":1.5152,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.878032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"61","issue":"3","first_page":"386","last_page":"398"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9825000166893005,"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":0.9677000045776367,"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":0.867436408996582},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6450958847999573},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5871836543083191},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.585284948348999},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5243834853172302},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5167969465255737},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.501967191696167},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4961453378200531},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49150073528289795},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.47667598724365234},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4700450003147125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39722850918769836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3901202380657196},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1312204897403717}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.867436408996582},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6450958847999573},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5871836543083191},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.585284948348999},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5243834853172302},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5167969465255737},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.501967191696167},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4961453378200531},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49150073528289795},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.47667598724365234},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4700450003147125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39722850918769836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3901202380657196},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1312204897403717},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1093/comjnl/bxx098","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxx098","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"},{"id":"pmh:oai:ir.lib.uth.gr:11615/74972","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/74972","pdf_url":null,"source":{"id":"https://openalex.org/S4306400243","display_name":"University of Thessaly Institutional Repository (University of Thessaly)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145722265","host_organization_name":"University of Thessaly","host_organization_lineage":["https://openalex.org/I145722265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Journal","raw_type":"journalArticle"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1494581921","https://openalex.org/W1539477445","https://openalex.org/W1978515644","https://openalex.org/W2013970953","https://openalex.org/W2069015717","https://openalex.org/W2071113239","https://openalex.org/W2086677639","https://openalex.org/W2094930182","https://openalex.org/W2097994458","https://openalex.org/W2103155997","https://openalex.org/W2125121047","https://openalex.org/W2133990480","https://openalex.org/W2139259611","https://openalex.org/W2148738951","https://openalex.org/W2326804586","https://openalex.org/W2511006541","https://openalex.org/W6674017165"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W1976205134","https://openalex.org/W1980381208","https://openalex.org/W2381570729","https://openalex.org/W4248336175","https://openalex.org/W3009369890","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W4312490297"],"abstract_inverted_index":{"The":[0,171],"Web":[1],"has":[2,133],"been":[3,55,135],"identified":[4],"to":[5,30,79,127,199],"consist":[6],"of":[7,11,43,49,62,67,84,92,117,130,144,159,182],"a":[8,27,31,75,82,97,114,120,142,156],"large":[9],"portion":[10],"content":[12],"that":[13,57],"cannot":[14],"be":[15,196],"crawled":[16],"by":[17,86,151],"general-purpose":[18],"search":[19,32,44],"engines":[20],"because":[21],"it":[22],"is":[23],"only":[24],"generated":[25],"after":[26],"valid":[28],"submission":[29],"interface.":[33],"Accessing":[34],"such":[35],"content,":[36],"however,":[37],"requires":[38],"the":[39,47,59,65,88,106,109,128,148,153,160,180],"location":[40],"and":[41,100,146,164,187],"identification":[42,66],"interfaces.":[45,69],"Towards":[46],"automation":[48],"this":[50,71],"task,":[51],"many":[52],"approaches":[53],"have":[54],"proposed":[56],"involve":[58],"manual":[60],"definition":[61],"rules":[63,85,95,149,173],"for":[64,108],"query":[68],"In":[70],"paper,":[72],"we":[73,111],"propose":[74],"rule":[76],"induction":[77],"approach":[78],"automatically":[80],"construct":[81],"set":[83],"searching":[87],"most":[89],"promising":[90],"subspace":[91],"all":[93],"possible":[94],"with":[96],"brute-force":[98],"method":[99],"information":[101],"theoretic":[102],"criteria.":[103],"To":[104],"specify":[105],"features":[107],"rules,":[110],"initially":[112],"make":[113],"descriptive":[115],"analysis":[116],"Yahoo":[118,161],"L11,":[119],"specialized":[121],"dataset":[122,163,166],"containing":[123],"complex":[124],"interfaces,":[125],"which":[126],"best":[129],"our":[131],"knowledge":[132],"not":[134],"used":[136,167],"in":[137,168,178],"previous":[138],"works.":[139,170],"We":[140],"perform":[141],"series":[143],"evaluations":[145],"present":[147],"constructed":[150],"running":[152],"algorithm":[154],"on":[155],"random":[157],"sample":[158],"L11":[162],"another":[165],"similar":[169],"resulting":[172],"yield":[174],"high":[175],"classification":[176],"accuracy":[177],"predicting":[179],"functionality":[181],"new,":[183],"previously":[184],"unseen":[185],"forms":[186],"since":[188],"humans":[189],"can":[190,195],"easily":[191,197],"interpret":[192],"them,":[193],"they":[194],"ported":[198],"any":[200],"application":[201],"as-is.":[202]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
