{"id":"https://openalex.org/W4240181401","doi":"https://doi.org/10.1109/asonam.2016.7752259","title":"Web user profiling using data redundancy","display_name":"Web user profiling using data redundancy","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W4240181401","doi":"https://doi.org/10.1109/asonam.2016.7752259"},"language":"en","primary_location":{"id":"doi:10.1109/asonam.2016.7752259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asonam.2016.7752259","pdf_url":null,"source":{"id":"https://openalex.org/S4363608003","display_name":"2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)","raw_type":"proceedings-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/A5102325476","display_name":"Xiaotao Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaotao Gu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120312551","display_name":"Hong Yang","orcid":"https://orcid.org/0009-0001-7805-4610"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Yang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100670350","display_name":"Jie Tang","orcid":"https://orcid.org/0000-0001-8602-7754"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Tang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100345321","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-6595-7661"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102325476"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8674,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82563824,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"358","last_page":"365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"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":0.9987000226974487,"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/T11106","display_name":"Data Management and Algorithms","score":0.9983000159263611,"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/T11719","display_name":"Data Quality and Management","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.8280596733093262},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7540051341056824},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6321703791618347},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.5206419825553894},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3563193678855896},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14686450362205505}],"concepts":[{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.8280596733093262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540051341056824},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6321703791618347},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.5206419825553894},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3563193678855896},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14686450362205505}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asonam.2016.7752259","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asonam.2016.7752259","pdf_url":null,"source":{"id":"https://openalex.org/S4363608003","display_name":"2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1519754362","https://openalex.org/W1540071626","https://openalex.org/W1576520375","https://openalex.org/W1660390307","https://openalex.org/W1946427028","https://openalex.org/W1977970897","https://openalex.org/W2004234600","https://openalex.org/W2022322548","https://openalex.org/W2040974535","https://openalex.org/W2046083725","https://openalex.org/W2058036501","https://openalex.org/W2098678088","https://openalex.org/W2099196804","https://openalex.org/W2130831177","https://openalex.org/W2147654806","https://openalex.org/W2161819491","https://openalex.org/W2250545651","https://openalex.org/W2741767968","https://openalex.org/W2994982620","https://openalex.org/W6634442568","https://openalex.org/W6674866097","https://openalex.org/W6742319595","https://openalex.org/W6771369255"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"The":[0,158],"study":[1],"of":[2,17,39,64,89],"Web":[3,66,90,120],"user":[4,20,42,91,115],"profiling":[5,92],"can":[6],"be":[7],"traced":[8],"back":[9],"to":[10,34,51,99,144],"30":[11],"years":[12],"ago,":[13],"with":[14,60,101,199],"the":[15,24,30,53,57,61,65,79,87,94,102,119,128,132,146,169,172,184,194],"goal":[16],"extracting":[18,114],"\u201csemantic\u201d-based":[19],"profile":[21,54,116],"attributes":[22,55,117],"from":[23,56,72,118],"unstructured":[25],"Web.":[26],"Despite":[27],"slight":[28],"differences,":[29],"general":[31],"method":[32,70,186],"is":[33],"first":[35],"identify":[36],"relevant":[37],"pages":[38],"a":[40,69,107,151,178],"specific":[41],"and":[43,75,167],"then":[44],"use":[45],"machine":[46],"learning":[47],"models":[48],"(e.g.,":[49],"CRFs)":[50],"extract":[52],"page.":[58],"However,":[59],"rapid":[62],"growth":[63],"volume,":[67],"such":[68],"suffers":[71],"data":[73,96,180],"redundancy":[74],"error":[76,126],"propagation":[77],"between":[78],"two":[80],"steps.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85,149],"revisit":[86],"problem":[88],"in":[93,135,197],"big":[95,122],"era,":[97],"trying":[98],"deal":[100],"new":[103],"challenges.":[104],"We":[105],"propose":[106,150],"simple":[108],"but":[109],"very":[110],"effective":[111],"approach":[112,129],"for":[113],"using":[121],"data.":[123],"To":[124,139],"avoid":[125],"propagation,":[127],"processes":[130],"all":[131],"extraction":[133,147,173,195],"subtasks":[134],"one":[136],"unified":[137],"model.":[138,157,174],"further":[140],"incorporate":[141],"human":[142,162],"knowledge":[143,163],"improve":[145],"performance,":[148],"Markov":[152],"logic":[153],"factor":[154],"graph":[155],"(MagicFG)":[156],"MagicFG":[159],"model":[160],"describes":[161],"as":[164],"first-order":[165],"logics":[166,170],"combines":[168],"into":[171],"Our":[175],"experiments":[176],"on":[177],"real":[179],"set":[181],"show":[182],"that":[183],"proposed":[185],"significantly":[187],"improves":[188],"(+4-6%;":[189],"p":[190],"\u226a":[191],"0.01,":[192],"t-test)":[193],"performance":[196],"comparison":[198],"several":[200],"baseline":[201],"methods.":[202]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}