{"id":"https://openalex.org/W1982678692","doi":"https://doi.org/10.1145/1060745.1060813","title":"Disambiguating Web appearances of people in a social network","display_name":"Disambiguating Web appearances of people in a social network","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W1982678692","doi":"https://doi.org/10.1145/1060745.1060813","mag":"1982678692"},"language":"en","primary_location":{"id":"doi:10.1145/1060745.1060813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1060745.1060813","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 World Wide Web - WWW '05","raw_type":"proceedings-article"},"type":"conference-abstract","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://works.bepress.com/andrew_mccallum/47/download/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005515091","display_name":"Ron Bekkerman","orcid":"https://orcid.org/0000-0001-5636-694X"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron Bekkerman","raw_affiliation_strings":["University of Massachusetts, Amherst, MA","University of Massachusetts, Amherst MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107835063","display_name":"Andrew McCallum","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew McCallum","raw_affiliation_strings":["University of Massachusetts, Amherst, MA","University of Massachusetts, Amherst MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University of Massachusetts, Amherst MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":274,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"463","last_page":"463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9943000078201294,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9943000078201294,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9846000075340271,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9817000031471252,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7661771774291992},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7135374546051025},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6441981792449951},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6367641687393188},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5684854984283447},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5645709037780762},{"id":"https://openalex.org/keywords/hits-algorithm","display_name":"HITS algorithm","score":0.46832209825515747},{"id":"https://openalex.org/keywords/social-network","display_name":"Social network (sociolinguistics)","score":0.4682271182537079},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.46476492285728455},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.3701111376285553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27958929538726807},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.2265775203704834},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.18212231993675232}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7661771774291992},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7135374546051025},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6441981792449951},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6367641687393188},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5684854984283447},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5645709037780762},{"id":"https://openalex.org/C195409031","wikidata":"https://www.wikidata.org/wiki/Q1031957","display_name":"HITS algorithm","level":5,"score":0.46832209825515747},{"id":"https://openalex.org/C4727928","wikidata":"https://www.wikidata.org/wiki/Q17164759","display_name":"Social network (sociolinguistics)","level":3,"score":0.4682271182537079},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.46476492285728455},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.3701111376285553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27958929538726807},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.2265775203704834},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.18212231993675232}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1060745.1060813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1060745.1060813","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 World Wide Web - WWW '05","raw_type":"proceedings-article"},{"id":"pmh:oai:works.bepress.com:andrew_mccallum-1069","is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/47","pdf_url":"https://works.bepress.com/andrew_mccallum/47/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andrew McCallum","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.152.2005","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.152.2005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ciir.cs.umass.edu/pubfiles/ir-382.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.59.3154","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.59.3154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2005.org/cdrom/docs/p463.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:works.bepress.com:andrew_mccallum-1069","is_oa":true,"landing_page_url":"https://works.bepress.com/andrew_mccallum/47","pdf_url":"https://works.bepress.com/andrew_mccallum/47/download/","source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Andrew McCallum","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332162","display_name":"Centers for Disease Control and Prevention","ror":"https://ror.org/042twtr12"},{"id":"https://openalex.org/F4320332749","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1982678692.pdf","grobid_xml":"https://content.openalex.org/works/W1982678692.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W70969037","https://openalex.org/W1502876877","https://openalex.org/W1531783365","https://openalex.org/W1540550673","https://openalex.org/W1604792744","https://openalex.org/W1676212923","https://openalex.org/W1964937891","https://openalex.org/W2010425028","https://openalex.org/W2040041305","https://openalex.org/W2060314721","https://openalex.org/W2060683726","https://openalex.org/W2103723258","https://openalex.org/W2113227740","https://openalex.org/W2133236963","https://openalex.org/W2142276227","https://openalex.org/W2147880316","https://openalex.org/W2149956050","https://openalex.org/W2153911474","https://openalex.org/W2162337786","https://openalex.org/W2785356762","https://openalex.org/W2979454998"],"related_works":["https://openalex.org/W2387616437","https://openalex.org/W1588416135","https://openalex.org/W2008577673","https://openalex.org/W2295656603","https://openalex.org/W4254300012","https://openalex.org/W2096839908","https://openalex.org/W1486482441","https://openalex.org/W1999548128","https://openalex.org/W1536079598","https://openalex.org/W2156928086"],"abstract_inverted_index":{"Say":[0],"you":[1,27],"are":[2,23,32,46,52],"looking":[3,47],"for":[4,16,48,71],"information":[5],"about":[6,24,33],"a":[7,92,107],"particular":[8],"person.":[9],"A":[10],"search":[11],"engine":[12],"returns":[13],"many":[14],"pages":[15,22,113],"that":[17],"person's":[18],"name":[19],"but":[20],"which":[21,31],"the":[25,40,81],"person":[26],"care":[28],"about,":[29],"and":[30,105],"other":[34],"people":[35,50],"who":[36,51],"happen":[37],"to":[38],"have":[39],"same":[41],"name?":[42],"Furthermore,":[43],"if":[44],"we":[45,59,103],"multiple":[49],"related":[53],"in":[54,124,126],"some":[55],"way,":[56],"how":[57],"can":[58],"best":[60],"leverage":[61],"this":[62,73,131],"social":[63],"network?":[64],"This":[65],"paper":[66],"presents":[67],"two":[68],"unsupervised":[69],"frameworks":[70],"solving":[72],"problem:":[74],"one":[75],"based":[76],"on":[77,118],"link":[78],"structure":[79],"of":[80,91,109],"Web":[82,112],"pages,":[83],"another":[84],"using":[85],"Agglomerative/Conglomerative":[86],"Double":[87],"Clustering":[88],"(A/CDC)---an":[89],"application":[90],"recently":[93],"introduced":[94],"multi-way":[95],"distributional":[96],"clustering":[97,138],"method.":[98],"To":[99],"evaluate":[100],"our":[101,133],"methods,":[102],"collected":[104],"hand-labeled":[106],"dataset":[108,132],"over":[110,144],"1000":[111],"retrieved":[114],"from":[115],"Google":[116],"queries":[117],"12":[119],"personal":[120],"names":[121],"appearing":[122],"together":[123],"someones":[125],"an":[127],"email":[128],"folder.":[129],"On":[130],"methods":[134],"outperform":[135],"traditional":[136],"agglomerative":[137],"by":[139],"more":[140],"than":[141],"20%,":[142],"achieving":[143],"80%":[145],"F-measure.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":26}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}