{"id":"https://openalex.org/W2057302324","doi":"https://doi.org/10.4304/jsw.9.3.641-647","title":"A DOM-based Anchor-Hop-T Method for Web Application Information Extraction","display_name":"A DOM-based Anchor-Hop-T Method for Web Application Information Extraction","publication_year":2014,"publication_date":"2014-03-01","ids":{"openalex":"https://openalex.org/W2057302324","doi":"https://doi.org/10.4304/jsw.9.3.641-647","mag":"2057302324"},"language":"en","primary_location":{"id":"doi:10.4304/jsw.9.3.641-647","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.9.3.641-647","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/A5100320635","display_name":"Yuanyuan Zhang","orcid":"https://orcid.org/0000-0001-9738-604X"},"institutions":[{"id":"https://openalex.org/I114539943","display_name":"Zhejiang Chinese Medical University","ror":"https://ror.org/04epb4p87","country_code":"CN","type":"education","lineage":["https://openalex.org/I114539943"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Zhang","raw_affiliation_strings":["College of Information Technology, Zhejiang Chinese Medical University, Hangzhou 310053"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Technology, Zhejiang Chinese Medical University, Hangzhou 310053","institution_ids":["https://openalex.org/I114539943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071572820","display_name":"Qinyan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinyan Zhang","raw_affiliation_strings":["Computer Center, Zhejiang University, Hangzhou 310058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Center, Zhejiang University, Hangzhou 310058","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026177476","display_name":"Guanfu Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanfu Jiang","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou 315100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou 315100","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8086,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82493513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"9","issue":"3","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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9829000234603882,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9690999984741211,"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":0.9347518682479858},{"id":"https://openalex.org/keywords/hop","display_name":"Hop (telecommunications)","score":0.6875219941139221},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4944186210632324},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4584348797798157},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4312552809715271},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.42911767959594727},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32090669870376587},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.26777398586273193},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.06942075490951538}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9347518682479858},{"id":"https://openalex.org/C25906391","wikidata":"https://www.wikidata.org/wiki/Q1432381","display_name":"Hop (telecommunications)","level":2,"score":0.6875219941139221},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4944186210632324},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4584348797798157},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4312552809715271},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.42911767959594727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32090669870376587},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.26777398586273193},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.06942075490951538},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.4304/jsw.9.3.641-647","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.9.3.641-647","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:10.1.1.656.5629","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.656.5629","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/jsw0903641647/8985/","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W48146613","https://openalex.org/W2078304983","https://openalex.org/W2110138423","https://openalex.org/W2145948275","https://openalex.org/W2154498027","https://openalex.org/W2162340487","https://openalex.org/W2319844921","https://openalex.org/W4253826874","https://openalex.org/W6681762687"],"related_works":["https://openalex.org/W1980877334","https://openalex.org/W2117210722","https://openalex.org/W1978191894","https://openalex.org/W2589759689","https://openalex.org/W2018045843","https://openalex.org/W3146035416","https://openalex.org/W3214730437","https://openalex.org/W3125668480","https://openalex.org/W1999406711","https://openalex.org/W1901649692"],"abstract_inverted_index":{"Abstract\u2014In":[0],"order":[1,132],"to":[2,15,34,56,60,67,83,96,133,168,216,221],"implement":[3],"the":[4,10,38,75,97,104,110,120,128,175,223],"information":[5,17,64,145],"fusion":[6],"of":[7,21,99,112,127,177,225],"electronic":[8],"products,":[9],"widely":[11],"adopted":[12],"approach":[13],"is":[14,32,42,65,81,94,107,115,166,180],"extract":[16,63,169],"from":[18],"HTML":[19,41,100,149],"structure":[20,106],"business":[22],"Website":[23],"with":[24],"deeply":[25],"data":[26,39,57,98,172,204],"processing.":[27],"However,":[28],"modeling":[29],"Web":[30],"application":[31],"hard":[33],"be":[35,68,124,157],"solved":[36],"that":[37,102,164],"in":[40],"semi-formal":[43],"which":[44,185],"displayed":[45],"as":[46,182,202],"DOM":[47],"(Document":[48],"Object":[49],"Model)":[50],"tree":[51],"when":[52],"using":[53,161],"XML":[54],"schema":[55],"analysis.":[58],"How":[59],"understand":[61],"and":[62,78,154,159,192,209],"first":[66],"researched.":[69],"The":[70,148],"general":[71],"model":[72,93,143,188],"Anchor-Hop":[73],"considering":[74],"text":[76],"property":[77,80],"label":[79],"simple":[82],"handle":[84],"this":[85,137],"problem.":[86],"Therefore,":[87],"it":[88,165],"has":[89],"low":[90],"effectiveness.":[91],"This":[92],"sensitive":[95],"structure,":[101],"if":[103],"website":[105],"slightly":[108],"changed":[109,129],"issue":[111],"extraction":[113,121,135,146],"accuracy":[114],"encountered.":[116],"As":[117],"a":[118,140],"result,":[119],"rules":[122],"should":[123],"redefined":[125],"because":[126],"structure.":[130],"In":[131],"improve":[134],"efficiency,":[136],"paper":[138],"proposed":[139],"DOM-based":[141],"dynamic":[142],"Anchor-Hop-T":[144],"model.":[147],"tags":[150],"including":[151],"table,":[152],"ol":[153],"ul":[155],"can":[156],"searched":[158],"processed":[160],"XPath":[162],"so":[163],"convenience":[167],"corresponding":[170],"Anchor":[171,191,203,206],"block.":[173],"Furthermore,":[174],"location":[176],"Hop":[178,193],"point":[179,194],"considered":[181],"invariant,":[183],"by":[184],"our":[186,226],"new":[187],"based":[189],"on":[190],"introduces":[195],"more":[196],"concepts":[197],"for":[198],"extracting":[199],"information,":[200],"such":[201],"block,":[205],"locating":[207],"library":[208],"AH":[210],"relevance":[211],"value.":[212],"Finally,":[213],"we":[214],"try":[215],"give":[217],"out":[218],"an":[219],"experiment":[220],"demonstrate":[222],"applicability":[224],"approach.":[227],"Index":[228],"Terms\u2014Web":[229],"Application,":[230],"Information":[231],"Extraction,":[232]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}