{"id":"https://openalex.org/W2154099239","doi":"https://doi.org/10.1145/2337542.2337552","title":"Leveraging Social Bookmarks from Partially Tagged Corpus for Improved Web Page Clustering","display_name":"Leveraging Social Bookmarks from Partially Tagged Corpus for Improved Web Page Clustering","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W2154099239","doi":"https://doi.org/10.1145/2337542.2337552","mag":"2154099239"},"language":"en","primary_location":{"id":"doi:10.1145/2337542.2337552","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2337542.2337552","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","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/A5018606314","display_name":"Anusua Trivedi","orcid":"https://orcid.org/0000-0002-1315-2113"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anusua Trivedi","raw_affiliation_strings":["University of Utah, Salt Lake City"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029651089","display_name":"Piyush Rai","orcid":"https://orcid.org/0000-0003-0660-8925"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piyush Rai","raw_affiliation_strings":["University of Utah, Salt Lake City"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019928111","display_name":"Hal Daum\u00e9","orcid":"https://orcid.org/0000-0002-3760-345X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hal Daum\u00e9","raw_affiliation_strings":["University of Maryland, College Park"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037435182","display_name":"Scott L. DuVall","orcid":"https://orcid.org/0000-0002-4898-3865"},"institutions":[{"id":"https://openalex.org/I4210089864","display_name":"VA Salt Lake City Healthcare System","ror":"https://ror.org/007fyq698","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I2799886695","https://openalex.org/I4210089864","https://openalex.org/I4210113540"]},{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott L. Duvall","raw_affiliation_strings":["VA SLC Health Care System and University of Utah, Salt Lake City"],"affiliations":[{"raw_affiliation_string":"VA SLC Health Care System and University of Utah, Salt Lake City","institution_ids":["https://openalex.org/I4210089864","https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018606314"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":1.768,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87343047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"3","issue":"4","first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9943000078201294,"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":0.8779038190841675},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7295924425125122},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6946642398834229},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6308994889259338},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.492180734872818},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.4746849238872528},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4549027681350708},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.3291158080101013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21896100044250488}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8779038190841675},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7295924425125122},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6946642398834229},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6308994889259338},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.492180734872818},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.4746849238872528},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4549027681350708},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.3291158080101013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21896100044250488}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2337542.2337552","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2337542.2337552","pdf_url":null,"source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.220.9486","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.220.9486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal3.name/docs/daume11social.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3704801407","display_name":null,"funder_award_id":"IIS-0712764","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"},{"id":"https://openalex.org/G5537634345","display_name":null,"funder_award_id":"VA HSR HIR 08-204","funder_id":"https://openalex.org/F4320306127","funder_display_name":"U.S. Department of Veterans Affairs"}],"funders":[{"id":"https://openalex.org/F4320306127","display_name":"U.S. Department of Veterans Affairs","ror":"https://ror.org/05rsv9s98"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W29190566","https://openalex.org/W290923189","https://openalex.org/W1503951939","https://openalex.org/W1510073064","https://openalex.org/W1536156198","https://openalex.org/W1536675765","https://openalex.org/W1538021842","https://openalex.org/W1566499617","https://openalex.org/W1576667197","https://openalex.org/W1880262756","https://openalex.org/W1948350624","https://openalex.org/W1956647075","https://openalex.org/W1975903729","https://openalex.org/W2009761865","https://openalex.org/W2017588182","https://openalex.org/W2020842694","https://openalex.org/W2025341678","https://openalex.org/W2048239613","https://openalex.org/W2048679005","https://openalex.org/W2062955551","https://openalex.org/W2066180141","https://openalex.org/W2066340877","https://openalex.org/W2079361215","https://openalex.org/W2091808810","https://openalex.org/W2098401485","https://openalex.org/W2099799470","https://openalex.org/W2100235303","https://openalex.org/W2101100852","https://openalex.org/W2108346334","https://openalex.org/W2108502868","https://openalex.org/W2111700528","https://openalex.org/W2113616339","https://openalex.org/W2120721759","https://openalex.org/W2123576058","https://openalex.org/W2124101779","https://openalex.org/W2127218421","https://openalex.org/W2127816222","https://openalex.org/W2132914434","https://openalex.org/W2138127867","https://openalex.org/W2139212933","https://openalex.org/W2139596625","https://openalex.org/W2140095548","https://openalex.org/W2142674578","https://openalex.org/W2146756121","https://openalex.org/W2147709600","https://openalex.org/W2150352612","https://openalex.org/W2168186441","https://openalex.org/W2296319761","https://openalex.org/W2596342170","https://openalex.org/W2648403730","https://openalex.org/W2903158431","https://openalex.org/W3149375329","https://openalex.org/W3193477162","https://openalex.org/W4236965008","https://openalex.org/W4250589301","https://openalex.org/W4285719527","https://openalex.org/W6676974520","https://openalex.org/W6756615331"],"related_works":["https://openalex.org/W1519586109","https://openalex.org/W2051097555","https://openalex.org/W2055154498","https://openalex.org/W1541158057","https://openalex.org/W2626548695","https://openalex.org/W2548348270","https://openalex.org/W2017818230","https://openalex.org/W2885559332","https://openalex.org/W2074126298","https://openalex.org/W2102269195"],"abstract_inverted_index":{"Automatic":[0],"clustering":[1,28,105,136,221],"of":[2,8,40,55,92,103,119,184,196,260],"Web":[3,26,42,69,94,160,185,219,241,261],"pages":[4,242],"helps":[5],"a":[6,52,76,93,124,181,194,257],"number":[7,183,195,259],"information":[9,63,87,201],"retrieval":[10],"tasks,":[11],"such":[12,44,58],"as":[13,45,59,115],"improving":[14],"user":[15],"interfaces,":[16],"collection":[17],"clustering,":[18],"introducing":[19],"diversity":[20],"in":[21,142,202,238],"search":[22],"results,":[23],"etc.":[24],"Typically,":[25],"page":[27,95,161,220],"algorithms":[29],"use":[30,199],"only":[31,164,179,249,256],"features":[32],"extracted":[33],"from":[34],"the":[35,38,60,68,84,90,101,120,129,132,159,170,209,218,252],"page-text.":[36],"However,":[37],"advent":[39],"social-bookmarking":[41],"sites,":[43],"StumbleUpon.com":[46],"and":[47,113,122,206],"Delicious.com,":[48],"has":[49],"led":[50],"to":[51,88,154,214,243],"huge":[53],"amount":[54],"user-generated":[56],"content":[57],"social":[61,85,171,253],"tag":[62,86,200],"that":[64,82,127,150,167,198,208,235],"is":[65,163],"associated":[66],"with":[67,100,193],"pages.":[70,186,262],"In":[71,107],"this":[72,143],"article,":[73],"we":[74,110,248],"present":[75,147,174],"subspace":[77,126,190,210],"based":[78,191,211],"feature":[79],"extraction":[80],"approach":[81,153,192,212],"leverages":[83],"complement":[89],"page-contents":[91],"for":[96,175,180,255],"extracting":[97],"beter":[98],"features,":[99],"goal":[102],"improved":[104,215],"performance.":[106],"our":[108,152,189],"approach,":[109],"consider":[111],"page-text":[112],"tags":[114,172,245,254],"two":[116,133],"separate":[117],"views":[118],"data,":[121],"learn":[123],"shared":[125],"maximizes":[128],"correlation":[130],"between":[131],"views.":[134],"Any":[135],"algorithm":[137],"can":[138,236,250],"then":[139,146],"be":[140,155],"applied":[141],"subspace.":[144],"We":[145,187,223],"an":[148,231],"extension":[149,234],"allows":[151],"applicable":[156],"even":[157],"if":[158,247],"corpus":[162],"partially":[165],"tagged,":[166],"is,":[168],"when":[169],"are":[173],"not":[176],"all,":[177],"but":[178],"small":[182,258],"compare":[188],"baselines":[197],"various":[203],"other":[204],"ways,":[205],"show":[207],"leads":[213],"performance":[216],"on":[217],"task.":[222],"also":[224],"discuss":[225],"some":[226],"possible":[227],"future":[228],"work":[229],"including":[230],"active":[232],"learning":[233],"help":[237],"choosing":[239],"which":[240],"get":[244,251],"for,":[246]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}