{"id":"https://openalex.org/W2072669000","doi":"https://doi.org/10.1145/2484028.2484157","title":"Author disambiguation by hierarchical agglomerative clustering with adaptive stopping criterion","display_name":"Author disambiguation by hierarchical agglomerative clustering with adaptive stopping criterion","publication_year":2013,"publication_date":"2013-07-28","ids":{"openalex":"https://openalex.org/W2072669000","doi":"https://doi.org/10.1145/2484028.2484157","mag":"2072669000"},"language":"en","primary_location":{"id":"doi:10.1145/2484028.2484157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","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/A5085349440","display_name":"Lei Cen","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lei Cen","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057346703","display_name":"Eduard Dragut","orcid":"https://orcid.org/0000-0002-3103-054X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eduard C. Dragut","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101718341","display_name":"Luo Si","orcid":"https://orcid.org/0000-0002-3263-234X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luo Si","raw_affiliation_strings":["Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026923999","display_name":"Mourad Ouzzani","orcid":"https://orcid.org/0000-0002-4035-3025"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mourad Ouzzani","raw_affiliation_strings":["Qatar Computing Research Institute, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085349440"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":3.4143,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.92575523,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"741","last_page":"744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.97079998254776,"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":0.7889975309371948},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6814767122268677},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.681282103061676},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5942654609680176},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5178976058959961},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.5032355189323425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48935168981552124},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47666293382644653},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4651312232017517},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4620454013347626},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4103868007659912},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3421197831630707},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.24630188941955566},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.17657005786895752},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14045879244804382}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7889975309371948},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6814767122268677},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.681282103061676},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5942654609680176},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5178976058959961},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.5032355189323425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48935168981552124},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47666293382644653},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4651312232017517},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4620454013347626},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4103868007659912},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3421197831630707},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.24630188941955566},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.17657005786895752},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14045879244804382},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2484028.2484157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:docs.lib.purdue.edu:ccpubs-1525","is_oa":false,"landing_page_url":"https://docs.lib.purdue.edu/ccpubs/544","pdf_url":null,"source":{"id":"https://openalex.org/S4377196310","display_name":"Purdue e-Pubs (Purdue University System)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801333002","host_organization_name":"Purdue University System","host_organization_lineage":["https://openalex.org/I2801333002"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cyber Center Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W173346298","https://openalex.org/W1597405158","https://openalex.org/W1880262756","https://openalex.org/W1964879903","https://openalex.org/W1982690612","https://openalex.org/W2056826404","https://openalex.org/W2087183379","https://openalex.org/W2101599977","https://openalex.org/W2104511295","https://openalex.org/W2107699930","https://openalex.org/W2108991785","https://openalex.org/W2120623936","https://openalex.org/W2129558264","https://openalex.org/W2136517229","https://openalex.org/W2147107544","https://openalex.org/W2148019918","https://openalex.org/W2162337786","https://openalex.org/W2296319761","https://openalex.org/W4250589301","https://openalex.org/W4251512373"],"related_works":["https://openalex.org/W4292477917","https://openalex.org/W2034251629","https://openalex.org/W2592952084","https://openalex.org/W2534504385","https://openalex.org/W4385569388","https://openalex.org/W3202164597","https://openalex.org/W2060765209","https://openalex.org/W2076085869","https://openalex.org/W3094186615","https://openalex.org/W2130194910"],"abstract_inverted_index":{"Entity":[0],"disambiguation":[1,18,24],"is":[2,32,58],"an":[3],"important":[4],"step":[5],"in":[6,25,96],"many":[7],"information":[8],"retrieval":[9],"applications.":[10],"This":[11,98],"paper":[12],"proposes":[13],"new":[14],"research":[15],"for":[16,35],"entity":[17],"with":[19,53,77,115],"the":[20,39,94,128,131],"focus":[21],"of":[22,65,75,87,118,130],"name":[23,42],"digital":[26],"libraries.":[27],"In":[28],"particular,":[29],"pairwise":[30],"similarity":[31],"first":[33],"learned":[34],"publications":[36,66,76],"that":[37,67],"share":[38,68],"same":[40,70],"author":[41,79],"string":[43],"(ANS)":[44],"and":[45],"then":[46],"a":[47,63,69,85,110,116],"novel":[48],"Hierarchical":[49],"Agglomerative":[50],"Clustering":[51],"approach":[52,83],"Adaptive":[54],"Stopping":[55],"Criterion":[56],"(HACASC)":[57],"proposed":[59,132],"to":[60,72,91,126],"adaptively":[61],"cluster":[62],"set":[64],"ANS":[71],"individual":[73],"clusters":[74],"different":[78],"identities.":[80],"The":[81],"HACASC":[82,133],"utilizes":[84],"mixture":[86],"kernel":[88],"ridge":[89],"regressions":[90],"intelligently":[92],"determine":[93],"threshold":[95],"clustering.":[97],"obtains":[99],"more":[100,119],"appropriate":[101],"clustering":[102],"granularity":[103],"than":[104,120],"non-adaptive":[105],"stopping":[106],"criterion.":[107],"We":[108],"conduct":[109],"large":[111],"scale":[112],"empirical":[113],"study":[114],"dataset":[117],"2":[121],"million":[122],"publication":[123],"record":[124],"pairs":[125],"demonstrate":[127],"advantage":[129],"approach.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}