{"id":"https://openalex.org/W1998152556","doi":"https://doi.org/10.4304/jsw.9.12.3057-3062","title":"Research on Deep Web Query Interface Clustering Based on Hadoop","display_name":"Research on Deep Web Query Interface Clustering Based on Hadoop","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1998152556","doi":"https://doi.org/10.4304/jsw.9.12.3057-3062","mag":"1998152556"},"language":"en","primary_location":{"id":"doi:10.4304/jsw.9.12.3057-3062","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.9.12.3057-3062","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","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/A5008213911","display_name":"Baohua Qiang","orcid":"https://orcid.org/0000-0002-3469-6590"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baohua Qiang","raw_affiliation_strings":["Guangxi Key Lab of Trusted Software, Guilin University of Electronic Technology, Guilin 541000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Trusted Software, Guilin University of Electronic Technology, Guilin 541000","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422092","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-8132-6250"},"institutions":[{"id":"https://openalex.org/I198645480","display_name":"North China University of Water Resources and Electric Power","ror":"https://ror.org/03acrzv41","country_code":"CN","type":"education","lineage":["https://openalex.org/I198645480"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["North China University of Water Resources and Electric Power, Zhengzhou 450045"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North China University of Water Resources and Electric Power, Zhengzhou 450045","institution_ids":["https://openalex.org/I198645480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367907","display_name":"Yufeng Wang","orcid":"https://orcid.org/0000-0001-8713-3153"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Wang","raw_affiliation_strings":["The 54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang 050000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The 54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang 050000","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100746961","display_name":"Qian He","orcid":"https://orcid.org/0000-0003-3020-2896"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian He","raw_affiliation_strings":["Guangxi Key Lab of Trusted Software, Guilin University of Electronic Technology, Guilin 541000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Trusted Software, Guilin University of Electronic Technology, Guilin 541000","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318285","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-8077-7025"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Guangxi Key Lab of Trusted Software, Guilin University of Electronic Technology, Guilin 541000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Trusted Software, Guilin University of Electronic Technology, Guilin 541000","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115595436","display_name":"Sai Wang","orcid":"https://orcid.org/0009-0001-9044-7927"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sai Wang","raw_affiliation_strings":["Guangxi Key Lab of Trusted Software, Guilin University of Electronic Technology, Guilin 541000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Key Lab of Trusted Software, Guilin University of Electronic Technology, Guilin 541000","institution_ids":["https://openalex.org/I5343935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.1569009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"9","issue":"12","first_page":null,"last_page":null},"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/T11478","display_name":"Caching and Content Delivery","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9424823522567749},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5621035099029541},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.52752286195755},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.5141990184783936},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4792206883430481},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.46425682306289673},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34442105889320374},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33808183670043945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22381114959716797},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.19466039538383484},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18446257710456848},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.103150874376297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9424823522567749},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5621035099029541},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.52752286195755},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.5141990184783936},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4792206883430481},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.46425682306289673},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34442105889320374},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33808183670043945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22381114959716797},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.19466039538383484},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18446257710456848},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.103150874376297},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4304/jsw.9.12.3057-3062","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.9.12.3057-3062","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.664.9329","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.664.9329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ojs.academypublisher.com/index.php/jsw/article/download/jsw091230573062/10595/","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1598064945","https://openalex.org/W2013970953","https://openalex.org/W2019106661","https://openalex.org/W2074306108","https://openalex.org/W2101997700","https://openalex.org/W2113620297","https://openalex.org/W2114541504","https://openalex.org/W2125969310","https://openalex.org/W2128483847","https://openalex.org/W2141526367","https://openalex.org/W2160189941","https://openalex.org/W2165612380","https://openalex.org/W2166946830","https://openalex.org/W3144497322"],"related_works":["https://openalex.org/W152219301","https://openalex.org/W1590644098","https://openalex.org/W2353038018","https://openalex.org/W2073995228","https://openalex.org/W2547248270","https://openalex.org/W2103686661","https://openalex.org/W2243876543","https://openalex.org/W2091065008","https://openalex.org/W2992885595","https://openalex.org/W2372938158"],"abstract_inverted_index":{"Abstract\u2014How":[0],"to":[1,108],"cluster":[2],"different":[3],"query":[4,17,37,52,82],"interfaces":[5],"effectively":[6],"is":[7,90],"one":[8],"of":[9,29,34,60,69],"the":[10,26,32,47,70,96,118],"most":[11],"core":[12],"issues":[13],"when":[14],"generating":[15],"integrated":[16],"interface":[18,38,53,83],"on":[19,87],"Deep":[20,35,50,80],"Web":[21,36,51,81],"integration":[22],"domain.":[23],"However,":[24],"with":[25],"rapid":[27],"development":[28],"Internet":[30],"technology,":[31],"number":[33],"shows":[39],"an":[40],"explosive":[41],"growth":[42],"trend.":[43],"For":[44],"this":[45],"reason,":[46],"traditional":[48],"stand-alone":[49],"clustering":[54,84],"approaches":[55],"encounter":[56],"bottlenecks":[57],"in":[58,94],"terms":[59],"time":[61],"complexity":[62],"and":[63,74,92,101,124],"space":[64],"complexity.":[65],"After":[66],"further":[67],"study":[68],"Hadoop":[71,88,129],"distributed":[72],"platforms":[73],"Map":[75],"Reduce":[76],"programming":[77],"model,":[78],"a":[79],"algorithm":[85,120],"based":[86],"platform":[89],"designed":[91],"implemented,":[93],"which":[95],"Vector":[97],"Space":[98],"Model":[99],"(VSM)":[100],"Latent":[102],"Semantic":[103],"Analysis":[104],"(LSA)":[105],"are":[106],"employed":[107],"represent":[109],"\u201cQuery":[110],"Interfaces-Attributes\u201d":[111],"relationships.":[112],"The":[113],"experimental":[114],"results":[115],"show":[116],"that":[117],"proposed":[119],"has":[121],"better":[122],"scalability":[123],"speedup":[125],"ratio":[126],"by":[127],"using":[128],"architecture.":[130]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
