{"id":"https://openalex.org/W2146509817","doi":"https://doi.org/10.1145/1951365.1951421","title":"Link-based hidden attribute discovery for objects on Web","display_name":"Link-based hidden attribute discovery for objects on Web","publication_year":2011,"publication_date":"2011-03-21","ids":{"openalex":"https://openalex.org/W2146509817","doi":"https://doi.org/10.1145/1951365.1951421","mag":"2146509817"},"language":"en","primary_location":{"id":"doi:10.1145/1951365.1951421","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1951365.1951421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Extending Database Technology","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/A5057374456","display_name":"Jiuming Huang","orcid":"https://orcid.org/0000-0001-9641-9030"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiuming Huang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China and Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China and Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I170215575","https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063351917","display_name":"Haixun Wang","orcid":"https://orcid.org/0009-0007-0773-7004"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haixun Wang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030424204","display_name":"Yan Jia","orcid":"https://orcid.org/0000-0001-8012-5097"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Jia","raw_affiliation_strings":["National University of Defense Technology, Changsha, China","National University of Defense, Technology, ChangSha, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense, Technology, ChangSha, China#TAB#","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017633018","display_name":"Ariel Fuxman","orcid":"https://orcid.org/0009-0003-6760-997X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ariel Fuxman","raw_affiliation_strings":["Microsoft Research, Mountain View, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Mountain View, California","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057374456"],"corresponding_institution_ids":["https://openalex.org/I170215575","https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":3.0555,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.93166019,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"473","last_page":"484"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9810000061988831,"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/T13976","display_name":"Web visibility and informetrics","score":0.9736999869346619,"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":0.8292064070701599},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7014716863632202},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6591739654541016},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.6127433180809021},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5773659944534302},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5473672151565552},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5154557824134827},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5071859359741211},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4871925711631775},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.478863924741745},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4760056436061859},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32602035999298096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25439536571502686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292064070701599},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7014716863632202},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6591739654541016},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6127433180809021},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5773659944534302},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5473672151565552},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5154557824134827},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5071859359741211},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4871925711631775},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.478863924741745},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4760056436061859},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32602035999298096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25439536571502686},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1951365.1951421","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1951365.1951421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Extending Database Technology","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.429.252","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.429.252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.edbt.org/Proceedings/2011-Uppsala/papers/edbt/a42-huang.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324150","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W180474045","https://openalex.org/W1495062271","https://openalex.org/W1535992660","https://openalex.org/W1568339100","https://openalex.org/W1616576116","https://openalex.org/W1969221592","https://openalex.org/W1973483159","https://openalex.org/W1978137103","https://openalex.org/W1996869586","https://openalex.org/W2012575882","https://openalex.org/W2017782072","https://openalex.org/W2026080185","https://openalex.org/W2029020234","https://openalex.org/W2030412583","https://openalex.org/W2037802158","https://openalex.org/W2042070581","https://openalex.org/W2088600132","https://openalex.org/W2096496923","https://openalex.org/W2097597177","https://openalex.org/W2102189859","https://openalex.org/W2108126629","https://openalex.org/W2115900192","https://openalex.org/W2128836931","https://openalex.org/W2135479443","https://openalex.org/W2139061966","https://openalex.org/W2143309843","https://openalex.org/W2147237426","https://openalex.org/W2182824764","https://openalex.org/W2338237122"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W2083329789","https://openalex.org/W36911888","https://openalex.org/W2076910790","https://openalex.org/W2275993472","https://openalex.org/W2155199173","https://openalex.org/W1544491176"],"abstract_inverted_index":{"Information":[0],"extraction":[1,64],"from":[2,70],"the":[3,11,21,47,55,60,71,90,138,141,181,196],"Web":[4,12,56,73,120,134,159,179,194],"is":[5,24,44,52,83],"of":[6,80,132],"growing":[7],"importance.":[8],"Objects":[9],"on":[10,54,67,94,137,157,165],"are":[13,148,185,200],"often":[14],"associated":[15],"with":[16],"many":[17],"attributes":[18,29,106,153],"that":[19,58],"describe":[20],"objects.":[22,36,111],"It":[23],"essential":[25],"to":[26,33,104,110,150],"extract":[27],"these":[28],"and":[30,51,98,107,122,129,174,183,187,198,202],"map":[31,108],"them":[32,109],"their":[34],"corresponding":[35],"However,":[37],"much":[38],"attribute":[39,81],"information":[40,63,69,82],"about":[41],"an":[42,114],"object":[43,72,158],"hidden":[45,152],"in":[46,144],"dynamic":[48,91],"user":[49,92],"interaction":[50,93],"not":[53,154],"page":[57,74],"describes":[59],"object.":[61],"Existing":[62],"approaches":[65],"focus":[66],"getting":[68],"only,":[75],"which":[76],"means":[77],"a":[78,100],"lot":[79],"lost.":[84],"In":[85],"this":[86],"paper,":[87],"we":[88,123,147],"study":[89],"exploratory":[95,115,119],"search":[96,116],"Websites":[97],"propose":[99,124],"novel":[101],"link-based":[102],"approach":[103,164],"discover":[105,151],"We":[112,161,170],"build":[113],"model":[117],"for":[118,126],"sites,":[121],"algorithms":[125],"identifying,":[127],"clustering,":[128],"relationship":[130],"mining":[131],"related":[133],"pages":[135],"based":[136],"model.":[139],"Using":[140],"unsupervised":[142],"method":[143],"our":[145,163],"approach,":[146],"able":[149],"explicitly":[155],"shown":[156],"pages.":[160],"test":[162],"two":[166],"online":[167],"shopping":[168],"Websites.":[169],"achieve":[171],"high":[172],"precision":[173,182,197],"recall:":[175],"For":[176,190],"entirely":[177],"crawled":[178,192],"sites":[180,195],"recall":[184,199],"98%":[186,201],"97%":[188],"respectively.":[189,204],"randomly":[191],"(sampled)":[193],"80%":[203]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}