{"id":"https://openalex.org/W2026910242","doi":"https://doi.org/10.1145/2783258.2788601","title":"On the Reliability of Profile Matching Across Large Online Social Networks","display_name":"On the Reliability of Profile Matching Across Large Online Social Networks","publication_year":2015,"publication_date":"2015-08-07","ids":{"openalex":"https://openalex.org/W2026910242","doi":"https://doi.org/10.1145/2783258.2788601","mag":"2026910242"},"language":"en","primary_location":{"id":"doi:10.1145/2783258.2788601","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2783258.2788601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"preprint","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/A5033477761","display_name":"Oana Goga","orcid":"https://orcid.org/0000-0003-4635-5088"},"institutions":[{"id":"https://openalex.org/I4210121786","display_name":"Max Planck Institute for Software Systems","ror":"https://ror.org/02pe2kf23","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210121786"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oana Goga","raw_affiliation_strings":["MPI-SWS, Saarbrucken, Germany","Max Planck Institute for Software Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MPI-SWS, Saarbrucken, Germany","institution_ids":["https://openalex.org/I4210121786"]},{"raw_affiliation_string":"Max Planck Institute for Software Systems","institution_ids":["https://openalex.org/I4210121786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077502412","display_name":"Patrick Loiseau","orcid":"https://orcid.org/0000-0003-0674-3369"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Loiseau","raw_affiliation_strings":["EURECOM, Sophia-Antipolis, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015612893","display_name":"Robin Sommer","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robin Sommer","raw_affiliation_strings":["ICSI/LBNL, Berkeley, USA","International Computer Science Institute [Berkeley]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICSI/LBNL, Berkeley, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"International Computer Science Institute [Berkeley]","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058425984","display_name":"Renata Teixeira","orcid":"https://orcid.org/0009-0002-6996-3502"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Renata Teixeira","raw_affiliation_strings":["Inria, Paris, France","Laboratory of Information, Network and Communication Sciences","Measuring networks for enhancing USer Experience"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria, Paris, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Laboratory of Information, Network and Communication Sciences","institution_ids":[]},{"raw_affiliation_string":"Measuring networks for enhancing USer Experience","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067688305","display_name":"Krishna P. Gummadi","orcid":"https://orcid.org/0000-0003-1256-8800"},"institutions":[{"id":"https://openalex.org/I4210121786","display_name":"Max Planck Institute for Software Systems","ror":"https://ror.org/02pe2kf23","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210121786"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Krishna P. Gummadi","raw_affiliation_strings":["MPI-SWS, Saarbrucken, Germany","Max Planck Institute for Software Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MPI-SWS, Saarbrucken, Germany","institution_ids":["https://openalex.org/I4210121786"]},{"raw_affiliation_string":"Max Planck Institute for Software Systems","institution_ids":["https://openalex.org/I4210121786"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":44.5268,"has_fulltext":false,"cited_by_count":131,"citation_normalized_percentile":{"value":0.99791281,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1799","last_page":"1808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9987999796867371,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9987999796867371,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9987000226974487,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9975000023841858,"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/matching","display_name":"Matching (statistics)","score":0.8555882573127747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8063017129898071},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.736116349697113},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.7302851676940918},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6222035884857178},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5318282246589661},{"id":"https://openalex.org/keywords/social-network","display_name":"Social network (sociolinguistics)","score":0.5051344037055969},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4849708080291748},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3963339626789093},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35946187376976013},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33115947246551514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3166358172893524},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.23594635725021362},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.15844321250915527},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08054500818252563},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07997500896453857}],"concepts":[{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.8555882573127747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063017129898071},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.736116349697113},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.7302851676940918},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6222035884857178},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5318282246589661},{"id":"https://openalex.org/C4727928","wikidata":"https://www.wikidata.org/wiki/Q17164759","display_name":"Social network (sociolinguistics)","level":3,"score":0.5051344037055969},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4849708080291748},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3963339626789093},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35946187376976013},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33115947246551514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3166358172893524},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.23594635725021362},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.15844321250915527},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08054500818252563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07997500896453857},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2783258.2788601","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2783258.2788601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01162402v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-01162402","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"KDD'15: ACM SIGDD Conference on Knowledge Discovery and Data Mining, Aug 2015, Sydeny, Australia. ⟨10.1145/2783258.2788601⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W81175482","https://openalex.org/W196349407","https://openalex.org/W844742131","https://openalex.org/W1496564895","https://openalex.org/W1547612978","https://openalex.org/W1551909886","https://openalex.org/W1646278814","https://openalex.org/W1767117126","https://openalex.org/W1969890816","https://openalex.org/W1975937116","https://openalex.org/W1980680715","https://openalex.org/W1999483928","https://openalex.org/W2026910242","https://openalex.org/W2051287084","https://openalex.org/W2055345291","https://openalex.org/W2074407292","https://openalex.org/W2075633077","https://openalex.org/W2077738931","https://openalex.org/W2090659861","https://openalex.org/W2102086994","https://openalex.org/W2113105081","https://openalex.org/W2113839561","https://openalex.org/W2118978333","https://openalex.org/W2122750868","https://openalex.org/W2147734964","https://openalex.org/W2151103935","https://openalex.org/W2159675343","https://openalex.org/W2165424625","https://openalex.org/W2170379762","https://openalex.org/W2294919332","https://openalex.org/W2560545764"],"related_works":["https://openalex.org/W1975289146","https://openalex.org/W1603736412","https://openalex.org/W2105887828","https://openalex.org/W2087240539","https://openalex.org/W1972035260","https://openalex.org/W4236520801","https://openalex.org/W2122599759","https://openalex.org/W4304185162","https://openalex.org/W2061685118","https://openalex.org/W3006282800"],"abstract_inverted_index":{"Matching":[0],"the":[1,58,105,111,138,153,166,174,212,218,223],"profiles":[2,66,191,216],"of":[3,89,91,110,113,121,140,155,190,214],"a":[4,99,119,141,149,187],"user":[5,24],"across":[6,69],"multiple":[7],"online":[8,25],"social":[9,71,85,183],"networks":[10,86],"brings":[11,94],"opportunities":[12],"for":[13,123],"new":[14,21,96],"services":[15],"and":[16,128,134,221],"applications":[17],"as":[18,20,98],"well":[19],"insights":[22],"on":[23,50,211],"behavior,":[26],"yet":[27],"it":[28,38],"raises":[29],"serious":[30],"privacy":[31],"concerns.":[32],"Prior":[33],"literature":[34],"has":[35],"showed":[36],"that":[37,165,192],"is":[39,170,186],"possible":[40,114],"to":[41,60,136,151,194,203,226],"accurately":[42],"match":[43,65],"profiles,":[44],"but":[45,197],"their":[46],"evaluation":[47],"focused":[48],"only":[49],"sampled":[51],"datasets.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,62,147],"study":[57],"extent":[59],"which":[61,93,201],"can":[63],"reliably":[64],"in":[67,158,168,177,217,230],"practice,":[68],"real-world":[70],"networks,":[72,184],"by":[73],"exploiting":[74],"public":[75],"attributes,":[76,200],"i.e.,":[77],"information":[78],"users":[79,196],"publicly":[80],"provide":[81],"about":[82],"themselves.":[83],"Today's":[84],"have":[87,198],"hundreds":[88],"millions":[90,112],"users,":[92],"completely":[95],"challenges":[97],"reliable":[100],"matching":[101,107,142,156,215,228],"scheme":[102],"must":[103],"identify":[104],"correct":[106,224],"profile":[108,124],"out":[109],"profiles.":[115],"We":[116],"first":[117],"define":[118],"set":[120],"properties":[122],"attributes--Availability,":[125],"Consistency,":[126],"non-Impersonability,":[127],"Discriminability":[129],"(ACID)--that":[130],"are":[131],"both":[132],"necessary":[133],"sufficient":[135],"determine":[137],"reliability":[139],"scheme.":[143],"Using":[144],"these":[145],"properties,":[146],"propose":[148],"method":[150],"evaluate":[152,227],"accuracy":[154,167],"schemes":[157,229],"real":[159,219],"practical":[160],"cases.":[161],"Our":[162,207],"results":[163],"show":[164],"practice":[169],"significantly":[171],"lower":[172],"than":[173],"one":[175],"reported":[176],"prior":[178],"literature.":[179],"When":[180],"considering":[181],"entire":[182],"there":[185],"non-negligible":[188],"number":[189],"belong":[193],"different":[195],"similar":[199],"leads":[202],"many":[204],"false":[205],"matches.":[206],"paper":[208],"sheds":[209],"light":[210],"limits":[213],"world":[220],"illustrates":[222],"methodology":[225],"realistic":[231],"scenarios.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}