{"id":"https://openalex.org/W2788018346","doi":"https://doi.org/10.1145/3178876.3186018","title":"Leveraging Social Media Signals for Record Linkage","display_name":"Leveraging Social Media Signals for Record Linkage","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2788018346","doi":"https://doi.org/10.1145/3178876.3186018","mag":"2788018346"},"language":"en","primary_location":{"id":"doi:10.1145/3178876.3186018","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186018","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186018&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3186018&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036042858","display_name":"Andrew Schneider","orcid":"https://orcid.org/0000-0003-2482-1578"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew T. Schneider","raw_affiliation_strings":["Temple University, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"Temple University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I84392919"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078060919","display_name":"Arjun Mukherjee","orcid":"https://orcid.org/0000-0002-8896-604X"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arjun Mukherjee","raw_affiliation_strings":["University of Houston, Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057346703","display_name":"Eduard Dragut","orcid":"https://orcid.org/0000-0002-3103-054X"},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eduard C. Dragut","raw_affiliation_strings":["Temple University, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"Temple University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I84392919"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036042858"],"corresponding_institution_ids":["https://openalex.org/I84392919"],"apc_list":null,"apc_paid":null,"fwci":0.8825,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76869882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1195","last_page":"1204"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9878000020980835,"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/T10028","display_name":"Topic Modeling","score":0.9803000092506409,"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":0.729571521282196},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.558613657951355},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5492241382598877},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.50987708568573},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.29283618927001953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.729571521282196},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.558613657951355},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5492241382598877},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.50987708568573},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29283618927001953},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3178876.3186018","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186018","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186018&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3178876.3186018","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3178876.3186018","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3186018&type=pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1711564787","display_name":"TWC: Small: Statistical Models for Opinion Spam Detection Leveraging Linguistic and Behavioral Cues","funder_award_id":"1527364","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2653471122","display_name":null,"funder_award_id":"1546480","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2788018346.pdf","grobid_xml":"https://content.openalex.org/works/W2788018346.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W195533127","https://openalex.org/W658020064","https://openalex.org/W1499253590","https://openalex.org/W1532325895","https://openalex.org/W1540269031","https://openalex.org/W1557103245","https://openalex.org/W1602412127","https://openalex.org/W1606801372","https://openalex.org/W1880262756","https://openalex.org/W1978394996","https://openalex.org/W1980804566","https://openalex.org/W1997927541","https://openalex.org/W2005876157","https://openalex.org/W2014415866","https://openalex.org/W2018268535","https://openalex.org/W2059299892","https://openalex.org/W2065259291","https://openalex.org/W2067566391","https://openalex.org/W2068115726","https://openalex.org/W2068549609","https://openalex.org/W2087183379","https://openalex.org/W2094963775","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097730395","https://openalex.org/W2097776316","https://openalex.org/W2109834209","https://openalex.org/W2117974736","https://openalex.org/W2123402141","https://openalex.org/W2125101937","https://openalex.org/W2133280805","https://openalex.org/W2139407700","https://openalex.org/W2148019918","https://openalex.org/W2148524305","https://openalex.org/W2150546140","https://openalex.org/W2151930506","https://openalex.org/W2153579005","https://openalex.org/W2158139315","https://openalex.org/W2164456230","https://openalex.org/W2164811795","https://openalex.org/W2171472464","https://openalex.org/W2294865516","https://openalex.org/W2295151155","https://openalex.org/W2301914932","https://openalex.org/W2511006541","https://openalex.org/W2950577311","https://openalex.org/W2951882581","https://openalex.org/W4213009331","https://openalex.org/W4251326898","https://openalex.org/W4291172695"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2487032012","https://openalex.org/W2211355040","https://openalex.org/W2808916796","https://openalex.org/W1501601012","https://openalex.org/W2176311362","https://openalex.org/W3088855600","https://openalex.org/W3012491082","https://openalex.org/W3211905090","https://openalex.org/W1936317645"],"abstract_inverted_index":{"Many":[0],"data-intensive":[1],"applications":[2],"collect":[3],"(structured)":[4],"data":[5],"from":[6,28],"a":[7,69,137],"variety":[8],"of":[9,24,44,53,80,107,123,131,157,171],"sources.":[10],"A":[11],"key":[12],"task":[13],"in":[14,110,115,141,177],"this":[15,48,76,163],"process":[16],"is":[17,21,103,164],"record":[18,42,72,145,179],"linkage,":[19],"which":[20],"the":[22,26,34,41,51,58,116,121,129,132,154,165,169,178],"problem":[23],"determining":[25],"records":[27],"these":[29],"sources":[30],"that":[31,74,104],"refer":[32],"to":[33,46,95],"same":[35],"real-world":[36,151],"entities.":[37],"Traditional":[38],"approaches":[39],"use":[40,84,170],"representation":[43],"entities":[45,56,99,108,176],"accomplish":[47],"task.":[49,181],"With":[50],"nascence":[52],"social":[54],"media,":[55],"on":[57,90],"Web":[59],"are":[60],"now":[61],"accompanied":[62],"by":[63],"user":[64,105,124,172],"generated":[65,173],"content.":[66],"We":[67,83,127],"present":[68],"method":[70,134,139],"for":[71],"linkage":[73,146,180],"uses":[75],"hitherto":[77],"untapped":[78],"source":[79],"entity":[81],"information.":[82],"document-based":[85],"distances,":[86,94],"with":[87,143],"an":[88],"emphasis":[89],"word":[91,117],"embedding":[92],"document":[93],"determine":[96],"if":[97],"two":[98],"match.":[100],"Our":[101],"rationale":[102],"evaluations":[106,125],"converge":[109],"semantic":[111],"content,":[112],"and":[113,140],"hence":[114],"embedded":[118],"space,":[119],"as":[120,136],"number":[122],"grows.":[126],"analyze":[128],"effectiveness":[130,156],"proposed":[133],"both":[135],"stand-alone":[138],"combination":[142],"record-based":[144],"methods.":[147],"Experimental":[148],"results":[149],"using":[150],"reviews":[152],"demonstrate":[153],"high":[155],"our":[158,161],"approach.":[159],"To":[160],"knowledge,":[162],"first":[166],"work":[167],"exploring":[168],"content":[174],"accompanying":[175]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}