{"id":"https://openalex.org/W2038876950","doi":"https://doi.org/10.1080/08839510802028447","title":"CRAWLING THE CONSTRUCTION WEB \u2013 A MACHINE-LEARNING APPROACH WITHOUT NEGATIVE EXAMPLES","display_name":"CRAWLING THE CONSTRUCTION WEB \u2013 A MACHINE-LEARNING APPROACH WITHOUT NEGATIVE EXAMPLES","publication_year":2008,"publication_date":"2008-05-09","ids":{"openalex":"https://openalex.org/W2038876950","doi":"https://doi.org/10.1080/08839510802028447","mag":"2038876950"},"language":"en","primary_location":{"id":"doi:10.1080/08839510802028447","is_oa":true,"landing_page_url":"https://doi.org/10.1080/08839510802028447","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/08839510802028447?download=true","source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.tandfonline.com/doi/pdf/10.1080/08839510802028447?download=true","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060465245","display_name":"Milo\u0161 Kova\u010devi\u0107","orcid":"https://orcid.org/0000-0002-8216-4564"},"institutions":[{"id":"https://openalex.org/I4068193","display_name":"University of Belgrade","ror":"https://ror.org/02qsmb048","country_code":"RS","type":"education","lineage":["https://openalex.org/I4068193"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Milo\u0161 Kova\u010devi\u0107","raw_affiliation_strings":["\n                   \n               University of Belgrade, School of Civil Engineering, Belgrade, Serbia","University of Belgrade, School of Civil Engineering, Belgrade, Serbia#TAB#"],"affiliations":[{"raw_affiliation_string":"\n                   \n               University of Belgrade, School of Civil Engineering, Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]},{"raw_affiliation_string":"University of Belgrade, School of Civil Engineering, Belgrade, Serbia#TAB#","institution_ids":["https://openalex.org/I4068193"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014166320","display_name":"Colin H. Davidson","orcid":null},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Colin H. Davidson","raw_affiliation_strings":["\n                   \n               University of Montreal, School of Architecture, Montreal, Quebec, Canada","University of Montreal, School of Architecture, Montreal, Quebec, Canada#TAB#"],"affiliations":[{"raw_affiliation_string":"\n                   \n               University of Montreal, School of Architecture, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I70931966"]},{"raw_affiliation_string":"University of Montreal, School of Architecture, Montreal, Quebec, Canada#TAB#","institution_ids":["https://openalex.org/I70931966"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014166320"],"corresponding_institution_ids":["https://openalex.org/I70931966"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":0.8849,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84088026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"22","issue":"5","first_page":"459","last_page":"482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9993000030517578,"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/T10260","display_name":"Software Engineering Research","score":0.9993000030517578,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9983000159263611,"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/T10028","display_name":"Topic Modeling","score":0.9800999760627747,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8734503984451294},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8304721117019653},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.776532769203186},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5370800495147705},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5224898457527161},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.5019464492797852},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.47155332565307617},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4223289489746094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38858360052108765},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34592175483703613},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3224813938140869},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.19225192070007324},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.11790242791175842}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8734503984451294},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8304721117019653},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.776532769203186},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5370800495147705},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5224898457527161},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.5019464492797852},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47155332565307617},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4223289489746094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38858360052108765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34592175483703613},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3224813938140869},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.19225192070007324},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.11790242791175842},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/08839510802028447","is_oa":true,"landing_page_url":"https://doi.org/10.1080/08839510802028447","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/08839510802028447?download=true","source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:grafar.grf.bg.ac.rs:123456789/196","is_oa":false,"landing_page_url":"https://grafar.grf.bg.ac.rs/handle/123456789/196","pdf_url":null,"source":{"id":"https://openalex.org/S4306402541","display_name":"GraFar (University of Belgrade, Faculty of Civil Engineering)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210101313","host_organization_name":"University Hospital Center Dr Dragi\u0161a Mi\u0161ovi\u0107","host_organization_lineage":["https://openalex.org/I4210101313"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Applied Artificial Intelligence","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1080/08839510802028447","is_oa":true,"landing_page_url":"https://doi.org/10.1080/08839510802028447","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/08839510802028447?download=true","source":{"id":"https://openalex.org/S125501549","display_name":"Applied Artificial Intelligence","issn_l":"0883-9514","issn":["0883-9514","1087-6545"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2038876950.pdf","grobid_xml":"https://content.openalex.org/works/W2038876950.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W160262995","https://openalex.org/W1489992655","https://openalex.org/W1509115762","https://openalex.org/W1563170230","https://openalex.org/W1570542661","https://openalex.org/W1576891672","https://openalex.org/W1614703486","https://openalex.org/W1966496085","https://openalex.org/W2001832505","https://openalex.org/W2005422315","https://openalex.org/W2005579877","https://openalex.org/W2014134732","https://openalex.org/W2017224880","https://openalex.org/W2017726337","https://openalex.org/W2044743392","https://openalex.org/W2045998703","https://openalex.org/W2066636486","https://openalex.org/W2075194837","https://openalex.org/W2077658674","https://openalex.org/W2118020653","https://openalex.org/W2121294789","https://openalex.org/W2124673015","https://openalex.org/W2128915886","https://openalex.org/W2132870739","https://openalex.org/W2133699278","https://openalex.org/W2139212933","https://openalex.org/W2141825421","https://openalex.org/W2147164982","https://openalex.org/W2149684865","https://openalex.org/W2156772624","https://openalex.org/W2156909104","https://openalex.org/W2156963321","https://openalex.org/W2158275940","https://openalex.org/W2160793660","https://openalex.org/W2162502927","https://openalex.org/W2162630660","https://openalex.org/W2170541679","https://openalex.org/W2435251607","https://openalex.org/W2538492099","https://openalex.org/W2939083804","https://openalex.org/W4212997115","https://openalex.org/W6653787752"],"related_works":["https://openalex.org/W2375180657","https://openalex.org/W2042034567","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W2137810919","https://openalex.org/W2358310581","https://openalex.org/W2274831913","https://openalex.org/W2352686120","https://openalex.org/W2019080882","https://openalex.org/W4385695127"],"abstract_inverted_index":{"&":[0],"Professionals":[1],"and":[2,43,108,119,172,240,256],"craftsmen":[3],"in":[4,14,96,127,185,236],"the":[5,24,35,73,83,93,125,128,157,201,206,209,213,230,237,250],"construction":[6,40,241],"sector":[7],"make":[8,20,220],"an":[9,68,98,198],"intensive":[10],"use":[11,22,116],"of":[12,23,75,78,85,183,232,234,244],"information":[13,26,146,214,248],"their":[15],"decision-making":[16],"processes":[17],"but":[18],"only":[19,142],"limited":[21],"abundant":[25],"that":[27,71,112,155,215,228],"is":[28,41,45,90,102,163,192,216,249],"potentially":[29],"available":[30],"to":[31,50,82,104,124,165,179,196,200,219,247],"them,":[32],"particularly":[33],"on":[34,92],"web.Consequently,":[36],"designs":[37],"are":[38,122,152],"impoverished,":[39],"defective,":[42],"innovation":[44],"delayed.To":[46],"facilitate":[47],"convivial":[48],"access":[49,246],"focused":[51],"information,":[52],"we":[53,65],"have":[54,66],"developed":[55,67],"a":[56,76,193],"question-and-answer":[57],"(Q-A)":[58],"system":[59],"(reported":[60],"elsewhere).To":[61],"support":[62],"this":[63,86],"system,":[64],"automated":[69],"crawler":[70,154],"permits":[72],"establishment":[74],"bank":[77],"relevant":[79],"pages,":[80],"adapted":[81],"needs":[84],"particular":[87],"industry-user":[88],"community.It":[89],"based":[91],"machine-learning":[94],"framework":[95,162],"which":[97,115],"intelligent":[99],"decision":[100],"unit":[101],"trained":[103],"distinguish":[105],"between":[106],"nontopic":[107],"informative":[109],"pages.We":[110],"show":[111],"standard":[113],"approaches":[114],"both":[117],"positive":[118,145,158],"negative":[120,129,137],"classes":[121],"sensitive":[123],"noise":[126],"class.We":[130],"propose":[131],"different":[132,186],"techniques":[133],"for":[134],"learning":[135,160],"without":[136],"examples,":[138],"since":[139],"initially":[140],"one":[141],"has":[143,225],"limited,":[144],"labeled":[147],"by":[148],"human":[149],"experts;":[150],"they":[151],"evaluated.Our":[153],"uses":[156],"examples-based":[159],"(PEBL)":[161],"able":[164],"collect":[166],"construction-oriented":[167],"pages":[168,184],"with":[169],"high":[170],"precision":[171],"discovery":[173],"rate.It":[174],"can":[175,205],"also":[176],"be":[177],"used":[178],"build":[180],"domain-specific":[181],"collections":[182],"scientific":[187],"or":[188],"professional":[189],"contexts.Currently,":[190],"there":[191],"pressing":[194],"need":[195],"provide":[197],"answer":[199],"following":[202],"question:":[203],"how":[204],"engineer":[207],"(or":[208],"architect)":[210],"possess":[211],"all":[212],"properly":[217],"required":[218],"professionally":[221],"correct":[222],"decisions?Indeed,":[223],"it":[224],"been":[226],"shown":[227],"among":[229],"causes":[231],"loss":[233],"productivity":[235],"building":[238],"design":[239],"process,":[242],"lack":[243],"effective":[245],"single":[251],"most":[252],"significant":[253],"factor":[254],"(Mohsini":[255],"Davidson":[257],"1991).":[258]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}
