{"id":"https://openalex.org/W2571099981","doi":"https://doi.org/10.1109/bigdata.2016.7840645","title":"Sampling labelled profile data for identity resolution","display_name":"Sampling labelled profile data for identity resolution","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2571099981","doi":"https://doi.org/10.1109/bigdata.2016.7840645","mag":"2571099981"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.lancs.ac.uk/id/eprint/82789/1/crosssampling_camera.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003587835","display_name":"Matthew Edwards","orcid":"https://orcid.org/0000-0001-8099-0646"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Matthew Edwards","raw_affiliation_strings":["School of Computing and Communications, Lancaster University, Lancaster, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing and Communications, Lancaster University, Lancaster, United Kingdom","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066876727","display_name":"Stephen Wattam","orcid":"https://orcid.org/0000-0002-0208-686X"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stephen Wattam","raw_affiliation_strings":["School of Computing and Communications, Lancaster University, Lancaster, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing and Communications, Lancaster University, Lancaster, United Kingdom","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058785189","display_name":"Paul Rayson","orcid":"https://orcid.org/0000-0002-1257-2191"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul Rayson","raw_affiliation_strings":["School of Computing and Communications, Lancaster University, Lancaster, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing and Communications, Lancaster University, Lancaster, United Kingdom","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034962802","display_name":"Awais Rashid","orcid":"https://orcid.org/0000-0002-0109-1341"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Awais Rashid","raw_affiliation_strings":["School of Computing and Communications, Lancaster University, Lancaster, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing and Communications, Lancaster University, Lancaster, United Kingdom","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003587835"],"corresponding_institution_ids":["https://openalex.org/I67415387"],"apc_list":null,"apc_paid":null,"fwci":2.2087,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91303494,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"8","issue":null,"first_page":"540","last_page":"547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9993000030517578,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9993000030517578,"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/T11045","display_name":"Privacy, Security, and Data Protection","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9764999747276306,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7178493738174438},{"id":"https://openalex.org/keywords/comparability","display_name":"Comparability","score":0.657906174659729},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6248398423194885},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5909207463264465},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.5777745842933655},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5028173327445984},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5016837120056152},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.48585984110832214},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4755777418613434},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42799896001815796},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3930068612098694},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.32614922523498535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15890079736709595},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09517568349838257},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08718833327293396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178493738174438},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.657906174659729},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6248398423194885},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5909207463264465},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.5777745842933655},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5028173327445984},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5016837120056152},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48585984110832214},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4755777418613434},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42799896001815796},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3930068612098694},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.32614922523498535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15890079736709595},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09517568349838257},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08718833327293396},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata.2016.7840645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.lancs.ac.uk:82789","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.lancs.ac.uk/id/eprint/82789/1/crosssampling_camera.pdf","source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:research-information.bris.ac.uk:openaire_cris_publications/bd2ac5be-88bb-4909-af4c-8b943de4de26","is_oa":false,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/bd2ac5be-88bb-4909-af4c-8b943de4de26","pdf_url":null,"source":{"id":"https://openalex.org/S7407055359","display_name":"Explore Bristol Research","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Edwards, M J, Wattam, S, Rayson, P & Rashid, A 2017, Sampling labelled profile data for identity resolution. in 2016 IEEE International Conference on Big Data, BigData 2016, Washington DC, USA, December 5-8, 2016. pp. 540-547. https://doi.org/10.1109/BigData.2016.7840645","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:eprints.lancs.ac.uk:82789","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.lancs.ac.uk/id/eprint/82789/1/crosssampling_camera.pdf","source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2571099981.pdf","grobid_xml":"https://content.openalex.org/works/W2571099981.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W118100702","https://openalex.org/W160003436","https://openalex.org/W1556918572","https://openalex.org/W1767117126","https://openalex.org/W1835452851","https://openalex.org/W1981590391","https://openalex.org/W1985769953","https://openalex.org/W2019377863","https://openalex.org/W2025328578","https://openalex.org/W2043077378","https://openalex.org/W2056765075","https://openalex.org/W2077738931","https://openalex.org/W2094120888","https://openalex.org/W2113105081","https://openalex.org/W2113839561","https://openalex.org/W2116099759","https://openalex.org/W2122750868","https://openalex.org/W2159675343","https://openalex.org/W2498798074","https://openalex.org/W4236804520","https://openalex.org/W6604828789","https://openalex.org/W6637977349"],"related_works":["https://openalex.org/W2365594754","https://openalex.org/W2575292835","https://openalex.org/W4287902769","https://openalex.org/W3001140700","https://openalex.org/W2995453361","https://openalex.org/W3021704418","https://openalex.org/W4390295458","https://openalex.org/W1990407237","https://openalex.org/W2092282998","https://openalex.org/W2053982300"],"abstract_inverted_index":{"Identity":[0],"resolution":[1,96],"capability":[2],"for":[3,9,138],"social":[4,71,119],"networking":[5,72],"profiles":[6,44],"is":[7,30],"important":[8],"a":[10,89,101],"range":[11],"of":[12,25,35,43,65,82,105,111,125,135],"purposes,":[13],"from":[14,45],"open-source":[15],"intelligence":[16],"applications":[17],"to":[18,37,68,100],"forming":[19],"semantic":[20],"web":[21],"connections.":[22],"Yet":[23],"replication":[24],"research":[26],"in":[27,94],"this":[28,129,136],"area":[29],"hampered":[31],"by":[32,54],"the":[33,41,69,78,112,123,133],"lack":[34],"access":[36,99],"ground-truth":[38],"data":[39,50],"linking":[40],"identities":[42],"different":[46],"networks.":[47,120],"Almost":[48],"all":[49],"sources":[51],"previously":[52],"used":[53],"researchers":[55,93,139],"are":[56,63],"no":[57],"longer":[58],"available,":[59],"and":[60,74,80,87,115,131,145],"historic":[61],"datasets":[62],"both":[64],"decreasing":[66],"relevance":[67],"modern":[70],"landscape":[73],"ethically":[75],"troublesome":[76],"regarding":[77],"preservation":[79],"publication":[81],"personal":[83],"data.":[84],"We":[85,121],"present":[86],"evaluate":[88],"method":[90,130],"which":[91],"provides":[92],"identity":[95],"with":[97],"easy":[98],"realistically-challenging":[102],"labelled":[103],"dataset":[104],"online":[106,118],"profiles,":[107],"drawing":[108],"on":[109],"four":[110],"currently":[113],"largest":[114],"most":[116],"influential":[117],"validate":[122],"comparability":[124],"samples":[126],"drawn":[127],"through":[128],"discuss":[132],"implications":[134],"mechanism":[137],"as":[140,142],"well":[141],"potential":[143],"alternatives":[144],"extensions.":[146]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}