{"id":"https://openalex.org/W4403948133","doi":"https://doi.org/10.3390/sym16111439","title":"A Semantic and Optimized Focused Crawler Based on Semantic Graph and Genetic Algorithm","display_name":"A Semantic and Optimized Focused Crawler Based on Semantic Graph and Genetic Algorithm","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403948133","doi":"https://doi.org/10.3390/sym16111439"},"language":"en","primary_location":{"id":"doi:10.3390/sym16111439","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym16111439","pdf_url":"https://www.mdpi.com/2073-8994/16/11/1439/pdf?version=1730297526","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/16/11/1439/pdf?version=1730297526","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101562765","display_name":"Wenhao Huang","orcid":"https://orcid.org/0000-0001-7557-1391"},"institutions":[{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Huang","raw_affiliation_strings":["School of Computer Science, South China Business College Guangdong University of Foreign Studies, Guangzhou 510545, China","School of Software Engineering, South China University of Technology, Guangzhou 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Business College Guangdong University of Foreign Studies, Guangzhou 510545, China","institution_ids":["https://openalex.org/I186272606"]},{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou 510006, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459390","display_name":"Xiaoyan Li","orcid":"https://orcid.org/0000-0001-7003-1644"},"institutions":[{"id":"https://openalex.org/I102345215","display_name":"Xihua University","ror":"https://ror.org/04gwtvf26","country_code":"CN","type":"education","lineage":["https://openalex.org/I102345215"]},{"id":"https://openalex.org/I186272606","display_name":"Guangdong University of Foreign Studies","ror":"https://ror.org/00fhc9y79","country_code":"CN","type":"education","lineage":["https://openalex.org/I186272606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Li","raw_affiliation_strings":["School of Computer and Software Engineering, Xihua University, Chengdu 610039, China","School of Computer Science, South China Business College Guangdong University of Foreign Studies, Guangzhou 510545, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Software Engineering, Xihua University, Chengdu 610039, China","institution_ids":["https://openalex.org/I102345215"]},{"raw_affiliation_string":"School of Computer Science, South China Business College Guangdong University of Foreign Studies, Guangzhou 510545, China","institution_ids":["https://openalex.org/I186272606"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036693904","display_name":"Xiao Zhou","orcid":"https://orcid.org/0000-0002-1331-7379"},"institutions":[{"id":"https://openalex.org/I102345215","display_name":"Xihua University","ror":"https://ror.org/04gwtvf26","country_code":"CN","type":"education","lineage":["https://openalex.org/I102345215"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Zhou","raw_affiliation_strings":["School of Computer and Software Engineering, Xihua University, Chengdu 610039, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Software Engineering, Xihua University, Chengdu 610039, China","institution_ids":["https://openalex.org/I102345215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088356478","display_name":"Deyu Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Deyu Qi","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou 510006, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101685776","display_name":"Jianqing Xi","orcid":"https://orcid.org/0000-0002-5009-520X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianqing Xi","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou 510006, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou 510006, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380197","display_name":"Wenjun Liu","orcid":"https://orcid.org/0009-0007-9240-5484"},"institutions":[{"id":"https://openalex.org/I102345215","display_name":"Xihua University","ror":"https://ror.org/04gwtvf26","country_code":"CN","type":"education","lineage":["https://openalex.org/I102345215"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenjun Liu","raw_affiliation_strings":["School of Computer and Software Engineering, Xihua University, Chengdu 610039, China","Sichuan Provincial Engineering Research Center of Hydroelectric Energy Power Equipment Technology, Xihua University, Chengdu 610039, China"],"raw_orcid":"https://orcid.org/0009-0007-9240-5484","affiliations":[{"raw_affiliation_string":"School of Computer and Software Engineering, Xihua University, Chengdu 610039, China","institution_ids":["https://openalex.org/I102345215"]},{"raw_affiliation_string":"Sichuan Provincial Engineering Research Center of Hydroelectric Energy Power Equipment Technology, Xihua University, Chengdu 610039, China","institution_ids":["https://openalex.org/I102345215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036646930","display_name":"Feiyu Zhao","orcid":"https://orcid.org/0000-0003-1704-0482"},"institutions":[{"id":"https://openalex.org/I102345215","display_name":"Xihua University","ror":"https://ror.org/04gwtvf26","country_code":"CN","type":"education","lineage":["https://openalex.org/I102345215"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyu Zhao","raw_affiliation_strings":["School of Computer and Software Engineering, Xihua University, Chengdu 610039, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Software Engineering, Xihua University, Chengdu 610039, China","institution_ids":["https://openalex.org/I102345215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088356478","https://openalex.org/A5100380197","https://openalex.org/A5101685776"],"corresponding_institution_ids":["https://openalex.org/I102345215","https://openalex.org/I90610280"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.6734,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79782261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"16","issue":"11","first_page":"1439","last_page":"1439"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.95169997215271,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9460999965667725,"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/web-crawler","display_name":"Web crawler","score":0.9248650074005127},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.8909382820129395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.794954776763916},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6955674886703491},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5613099336624146},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5151766538619995},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.4996187686920166},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.475142240524292},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.45224109292030334},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.42942050099372864},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4278453588485718},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2596355080604553},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1547047197818756},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.15149185061454773},{"id":"https://openalex.org/keywords/web-server","display_name":"Web server","score":0.11031347513198853}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9248650074005127},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.8909382820129395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794954776763916},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6955674886703491},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5613099336624146},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5151766538619995},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.4996187686920166},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.475142240524292},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.45224109292030334},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.42942050099372864},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4278453588485718},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2596355080604553},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1547047197818756},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.15149185061454773},{"id":"https://openalex.org/C11392498","wikidata":"https://www.wikidata.org/wiki/Q11288","display_name":"Web server","level":3,"score":0.11031347513198853},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/sym16111439","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym16111439","pdf_url":"https://www.mdpi.com/2073-8994/16/11/1439/pdf?version=1730297526","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3e467fdbeb244a428762a6d8efcba329","is_oa":false,"landing_page_url":"https://doaj.org/article/3e467fdbeb244a428762a6d8efcba329","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 16, Iss 11, p 1439 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/sym16111439","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym16111439","pdf_url":"https://www.mdpi.com/2073-8994/16/11/1439/pdf?version=1730297526","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6943549810","display_name":null,"funder_award_id":"61070015","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403948133.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W2140735141","https://openalex.org/W2165612380","https://openalex.org/W2399051749","https://openalex.org/W2568920572","https://openalex.org/W2771401735","https://openalex.org/W2971959138","https://openalex.org/W2998462652","https://openalex.org/W3007011226","https://openalex.org/W3092324237","https://openalex.org/W3092782196","https://openalex.org/W3113055796","https://openalex.org/W3129357156","https://openalex.org/W3179472575","https://openalex.org/W3204787348","https://openalex.org/W3205492715","https://openalex.org/W3211994119","https://openalex.org/W4205793898","https://openalex.org/W4214708877","https://openalex.org/W4214721941","https://openalex.org/W4221089296","https://openalex.org/W4224442743","https://openalex.org/W4288717981","https://openalex.org/W4293657795","https://openalex.org/W4309400599","https://openalex.org/W4313429811","https://openalex.org/W4365396578","https://openalex.org/W4384823976","https://openalex.org/W4385844420","https://openalex.org/W4390609863","https://openalex.org/W4391024884","https://openalex.org/W4391305039","https://openalex.org/W4395695509","https://openalex.org/W6684620663","https://openalex.org/W6767936078","https://openalex.org/W6773906474","https://openalex.org/W6784101355","https://openalex.org/W6784700415","https://openalex.org/W6797773445","https://openalex.org/W6804159996","https://openalex.org/W6852509623","https://openalex.org/W6855617122"],"related_works":["https://openalex.org/W2042034567","https://openalex.org/W1501777393","https://openalex.org/W2548443989","https://openalex.org/W2375180657","https://openalex.org/W2067523177","https://openalex.org/W2111427713","https://openalex.org/W2113184419","https://openalex.org/W2389761961","https://openalex.org/W4254300012","https://openalex.org/W1999548128"],"abstract_inverted_index":{"A":[0],"focused":[1,20,46,96,162,210],"crawler":[2,97,107,211],"automatically":[3],"retrieves,":[4],"organizes,":[5],"and":[6,16,40,55,94,102,130,169,185,202,216],"extracts":[7],"specific":[8],"topic-related":[9,219],"information":[10],"from":[11,49,222],"the":[12,23,60,78,86,117,138,149,154,159,174,179,194,208,223],"internet":[13],"for":[14],"analysis":[15,64],"application.":[17],"Currently,":[18],"most":[19],"crawlers":[21,47],"assess":[22],"relevance":[24,75,122],"of":[25,62,65,73,80,120,140,189,196],"web":[26,198,220],"pages":[27,221],"to":[28,59,136],"a":[29,92,113,127],"given":[30],"topic":[31,66,74,121],"through":[32],"methods":[33],"such":[34,51],"as":[35,52,68,70],"keyword":[36],"matching,":[37],"semantic":[38,63,93,114],"analysis,":[39],"link":[41],"structures.":[42],"However,":[43],"these":[44],"existing":[45],"suffer":[48],"issues":[50],"misleading":[53],"directions":[54],"reduced":[56],"accuracy":[57],"due":[58],"lack":[61],"terms,":[67],"well":[69],"biased":[71],"computation":[72],"caused":[76],"by":[77,111,125,178],"absence":[79],"effective":[81],"weighting":[82,118],"factors.":[83],"To":[84],"solve":[85],"above-mentioned":[87],"problems,":[88],"this":[89],"study":[90],"proposes":[91],"optimized":[95],"based":[98],"on":[99],"Semantic":[100],"Graph":[101],"Genetic":[103],"Algorithm.":[104],"The":[105,144],"proposed":[106,150,180,209],"eliminates":[108],"ambiguous":[109],"terms":[110,188],"constructing":[112],"graph,":[115],"optimizes":[116],"factors":[119],"with":[123,158],"asymmetry":[124],"using":[126],"genetic":[128],"algorithm,":[129],"combines":[131],"both":[132],"above":[133],"two":[134],"points":[135],"predict":[137],"priority":[139],"each":[141],"unvisited":[142],"hyperlink.":[143],"experiment":[145],"results":[146],"indicate":[147],"that":[148],"SG-GA":[151],"Crawler":[152],"improves":[153],"evaluation":[155,191],"indicators":[156],"compared":[157],"other":[160],"three":[161,190],"crawlers,":[163],"including":[164,193],"VSM":[165],"Crawler,":[166,168],"SSRM":[167],"SG":[170],"Crawler.":[171],"More":[172],"specifically,":[173],"percentage":[175],"improvement":[176],"achieved":[177],"method":[181],"exceeds":[182],"19%,":[183,184],"13%":[186],"in":[187],"indicators,":[192],"number":[195],"relevant":[197],"pages,":[199],"acquisition":[200],"rate,":[201],"average":[203],"relevance,":[204],"respectively.":[205],"In":[206],"conclusion,":[207],"can":[212],"grab":[213],"more":[214],"quantity":[215],"higher":[217],"quality":[218],"Internet.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
