{"id":"https://openalex.org/W2163190394","doi":"https://doi.org/10.1109/icdim.2008.4746736","title":"A survey in semantic web technologies-inspired focused crawlers","display_name":"A survey in semantic web technologies-inspired focused crawlers","publication_year":2008,"publication_date":"2008-11-01","ids":{"openalex":"https://openalex.org/W2163190394","doi":"https://doi.org/10.1109/icdim.2008.4746736","mag":"2163190394"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2008.4746736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://espace.curtin.edu.au/bitstream/20.500.11937/7518/2/116133_A%2520survey%2520in%2520semantic%2520Web04746736.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005267734","display_name":"Hai Dong","orcid":"https://orcid.org/0000-0002-7033-5688"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Hai Dong","raw_affiliation_strings":["Digital Ecosystems and Business Intelligence Institute, Curtin University of Technology, Australia"],"affiliations":[{"raw_affiliation_string":"Digital Ecosystems and Business Intelligence Institute, Curtin University of Technology, Australia","institution_ids":["https://openalex.org/I205640436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041615708","display_name":"Farookh Khadeer Hussain","orcid":"https://orcid.org/0000-0003-1513-8072"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Farookh Khadeer Hussain","raw_affiliation_strings":["Digital Ecosystems and Business Intelligence Institute, Curtin University of Technology, Australia"],"affiliations":[{"raw_affiliation_string":"Digital Ecosystems and Business Intelligence Institute, Curtin University of Technology, Australia","institution_ids":["https://openalex.org/I205640436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031465905","display_name":"Elizabeth Chang","orcid":"https://orcid.org/0000-0002-4439-1854"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Elizabeth Chang","raw_affiliation_strings":["Digital Ecosystems and Business Intelligence Institute, Curtin University of Technology, Australia"],"affiliations":[{"raw_affiliation_string":"Digital Ecosystems and Business Intelligence Institute, Curtin University of Technology, Australia","institution_ids":["https://openalex.org/I205640436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005267734"],"corresponding_institution_ids":["https://openalex.org/I205640436"],"apc_list":null,"apc_paid":null,"fwci":6.1227,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96312149,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"934","last_page":"936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10260","display_name":"Software Engineering Research","score":0.9815999865531921,"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":0.9750000238418579,"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":0.8148447871208191},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.7668274641036987},{"id":"https://openalex.org/keywords/social-semantic-web","display_name":"Social Semantic Web","score":0.6768637895584106},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.6438490152359009},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6258910894393921},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.5993779897689819},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.5977030396461487},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5648461580276489},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5496503114700317},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.4724937975406647},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.46268191933631897},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.42255374789237976},{"id":"https://openalex.org/keywords/semantic-analytics","display_name":"Semantic analytics","score":0.4171861410140991},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.2159450352191925},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.2133733332157135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148447871208191},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.7668274641036987},{"id":"https://openalex.org/C534406577","wikidata":"https://www.wikidata.org/wiki/Q7550843","display_name":"Social Semantic Web","level":3,"score":0.6768637895584106},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.6438490152359009},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6258910894393921},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.5993779897689819},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.5977030396461487},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5648461580276489},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5496503114700317},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.4724937975406647},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.46268191933631897},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.42255374789237976},{"id":"https://openalex.org/C148792806","wikidata":"https://www.wikidata.org/wiki/Q7449046","display_name":"Semantic analytics","level":4,"score":0.4171861410140991},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.2159450352191925},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.2133733332157135}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icdim.2008.4746736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746736","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","raw_type":"proceedings-article"},{"id":"pmh:oai:espace.curtin.edu.au:20.500.11937/7518","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11937/7518","pdf_url":"https://espace.curtin.edu.au/bitstream/20.500.11937/7518/2/116133_A%2520survey%2520in%2520semantic%2520Web04746736.pdf","source":{"id":"https://openalex.org/S4306401790","display_name":"eSpace (Curtin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205640436","host_organization_name":"Curtin University","host_organization_lineage":["https://openalex.org/I205640436"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:researchbank.rmit.edu.au:rmit:23549","is_oa":false,"landing_page_url":"http://researchbank.rmit.edu.au/view/rmit:23549","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:alma.61RMIT_INST:11247008950001341","is_oa":false,"landing_page_url":"http://doi.org/10.1109/ICDIM.2008.4746736","pdf_url":null,"source":{"id":"https://openalex.org/S4306402074","display_name":"RMIT Research Repository (RMIT University Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I82951845","host_organization_name":"RMIT University","host_organization_lineage":["https://openalex.org/I82951845"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/27384879","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/29974","is_oa":false,"landing_page_url":"http://hdl.handle.net/10453/29974","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:espace.curtin.edu.au:20.500.11937/7518","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11937/7518","pdf_url":"https://espace.curtin.edu.au/bitstream/20.500.11937/7518/2/116133_A%2520survey%2520in%2520semantic%2520Web04746736.pdf","source":{"id":"https://openalex.org/S4306401790","display_name":"eSpace (Curtin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205640436","host_organization_name":"Curtin University","host_organization_lineage":["https://openalex.org/I205640436"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320987","display_name":"Curtin University of Technology","ror":"https://ror.org/02n415q13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2163190394.pdf","grobid_xml":"https://content.openalex.org/works/W2163190394.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W154538122","https://openalex.org/W1503105411","https://openalex.org/W1527774729","https://openalex.org/W1571529277","https://openalex.org/W1967890081","https://openalex.org/W2038150775","https://openalex.org/W2100581921","https://openalex.org/W2116224704","https://openalex.org/W2164614639","https://openalex.org/W2165050266","https://openalex.org/W6634403407","https://openalex.org/W6684149752"],"related_works":["https://openalex.org/W1501777393","https://openalex.org/W2042034567","https://openalex.org/W2102887023","https://openalex.org/W2548443989","https://openalex.org/W2375180657","https://openalex.org/W3169657889","https://openalex.org/W2527201306","https://openalex.org/W2067523177","https://openalex.org/W2111427713","https://openalex.org/W2352357488"],"abstract_inverted_index":{"Crawlers":[0],"are":[1,66,108],"software":[2],"which":[3,65],"can":[4],"traverse":[5],"the":[6,14,17,40,51,76,81,103,138],"Internet":[7],"and":[8,44,92,125],"retrieve":[9],"Webpages":[10,99],"by":[11],"hyperlinks.":[12],"In":[13],"face":[15],"of":[16,42,57,69,87],"inundant":[18],"spam":[19],"Websites,":[20],"traditional":[21],"Web":[22,45,78,94],"crawlers":[23,33,60,70],"cannot":[24],"function":[25],"well":[26],"to":[27,38,74,90,102,132],"solve":[28],"this":[29,88,133],"problem.":[30],"Semantic":[31],"focused":[32,59,63],"utilize":[34,72],"semantic":[35,58],"web":[36],"technologies":[37,121],"analyze":[39],"semantics":[41],"hyperlinks":[43],"documents.":[46],"This":[47],"paper":[48],"briefly":[49],"reviews":[50],"recent":[52],"studies":[53],"on":[54],"one":[55],"category":[56],"-":[61,115],"ontology-based":[62],"crawlers,":[64],"a":[67],"series":[68],"that":[71],"ontologies":[73],"link":[75],"fetched":[77],"documents":[79],"with":[80,100,130],"ontological":[82],"concepts":[83],"(topics).":[84],"The":[85,128],"purpose":[86],"is":[89,135],"organize":[91],"categorize":[93],"documents,":[95],"or":[96],"filtering":[97],"irrelevant":[98],"regards":[101],"topics.":[104],"A":[105],"brief":[106],"comparison":[107,134],"made":[109,136],"among":[110],"these":[111],"crawlers,from":[112],"six":[113],"perspectives":[114],"domain,":[116],"working":[117],"environment,":[118],"special":[119],"functions,":[120],"utilized,":[122],"evaluation":[123,126],"metrics":[124],"results.":[127],"conclusion":[129],"respect":[131],"in":[137],"final":[139],"section.":[140]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
