{"id":"https://openalex.org/W1929731315","doi":"https://doi.org/10.18653/v1/w17-4411","title":"An Entity Resolution Approach to Isolate Instances of Human Trafficking Online","display_name":"An Entity Resolution Approach to Isolate Instances of Human Trafficking Online","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W1929731315","doi":"https://doi.org/10.18653/v1/w17-4411","mag":"1929731315"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-4411","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4411","pdf_url":"https://www.aclweb.org/anthology/W17-4411.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 3rd Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W17-4411.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035844932","display_name":"Chirag Nagpal","orcid":"https://orcid.org/0000-0003-2212-5392"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chirag Nagpal","raw_affiliation_strings":["Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114190243","display_name":"Kyle Miller","orcid":"https://orcid.org/0009-0005-2291-510X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Miller","raw_affiliation_strings":["Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057716290","display_name":"Benedikt Boecking","orcid":"https://orcid.org/0000-0003-4822-0531"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benedikt Boecking","raw_affiliation_strings":["Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037154494","display_name":"Artur Dubrawski","orcid":"https://orcid.org/0000-0002-2372-0831"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Artur Dubrawski","raw_affiliation_strings":["Carnegie Mellon University","Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035844932"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.6938,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.9005021,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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/T11644","display_name":"Spam and Phishing Detection","score":0.98089998960495,"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/T11860","display_name":"HIV, Drug Use, Sexual Risk","score":0.96670001745224,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7508672475814819},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7039341926574707},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6971002817153931},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.6529399752616882},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5974313020706177},{"id":"https://openalex.org/keywords/human-trafficking","display_name":"Human trafficking","score":0.5946179032325745},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.5776894092559814},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5580313205718994},{"id":"https://openalex.org/keywords/law-enforcement","display_name":"Law enforcement","score":0.5506658554077148},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4229119122028351},{"id":"https://openalex.org/keywords/enforcement","display_name":"Enforcement","score":0.411141574382782},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3975815773010254},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37550070881843567},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2937670350074768},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22528395056724548},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2206456959247589},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.09064963459968567},{"id":"https://openalex.org/keywords/criminology","display_name":"Criminology","score":0.0849529504776001},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.06735900044441223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508672475814819},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7039341926574707},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6971002817153931},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.6529399752616882},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5974313020706177},{"id":"https://openalex.org/C2984309518","wikidata":"https://www.wikidata.org/wiki/Q181784","display_name":"Human trafficking","level":2,"score":0.5946179032325745},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.5776894092559814},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5580313205718994},{"id":"https://openalex.org/C2780262971","wikidata":"https://www.wikidata.org/wiki/Q44554","display_name":"Law enforcement","level":2,"score":0.5506658554077148},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4229119122028351},{"id":"https://openalex.org/C2779777834","wikidata":"https://www.wikidata.org/wiki/Q4202277","display_name":"Enforcement","level":2,"score":0.411141574382782},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3975815773010254},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37550070881843567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2937670350074768},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22528395056724548},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2206456959247589},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.09064963459968567},{"id":"https://openalex.org/C73484699","wikidata":"https://www.wikidata.org/wiki/Q161733","display_name":"Criminology","level":1,"score":0.0849529504776001},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.06735900044441223},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/w17-4411","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4411","pdf_url":"https://www.aclweb.org/anthology/W17-4411.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 3rd Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1509.06659","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1509.06659","pdf_url":"https://arxiv.org/pdf/1509.06659","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:1929731315","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1509.06659","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1509.06659","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1509.06659","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-4411","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-4411","pdf_url":"https://www.aclweb.org/anthology/W17-4411.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 3rd Workshop on Noisy User-generated Text","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.5099999904632568,"display_name":"Gender equality"}],"awards":[{"id":"https://openalex.org/G3496183648","display_name":null,"funder_award_id":"-IJ-CX-","funder_id":"https://openalex.org/F4320337430","funder_display_name":"National Institute of Justice"},{"id":"https://openalex.org/G3994549050","display_name":null,"funder_award_id":"FA8750-14-2-0244","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8484321866","display_name":null,"funder_award_id":"2013-IJ-CX-K007","funder_id":"https://openalex.org/F4320337430","funder_display_name":"National Institute of Justice"}],"funders":[{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337430","display_name":"National Institute of Justice","ror":"https://ror.org/00v8p7w89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1929731315.pdf","grobid_xml":"https://content.openalex.org/works/W1929731315.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W1607983314","https://openalex.org/W2101234009","https://openalex.org/W2123561513","https://openalex.org/W2125910575"],"related_works":["https://openalex.org/W2963997288","https://openalex.org/W2605217525","https://openalex.org/W254113056","https://openalex.org/W2145124624","https://openalex.org/W3018042387","https://openalex.org/W2225606021","https://openalex.org/W3007025101","https://openalex.org/W2963970591","https://openalex.org/W2793216106","https://openalex.org/W3012275146","https://openalex.org/W2520082712","https://openalex.org/W3030713612","https://openalex.org/W2079659743","https://openalex.org/W2399003580","https://openalex.org/W2487678730","https://openalex.org/W2913201142","https://openalex.org/W3213941460","https://openalex.org/W3097680364","https://openalex.org/W3201319740","https://openalex.org/W2040348939"],"abstract_inverted_index":{"Human":[0],"trafficking":[1,39,72],"is":[2,40],"a":[3,41,54],"challenging":[4],"law":[5],"enforcement":[6],"problem,":[7],"and":[8,27,83,96],"traces":[9],"of":[10,12,30,38,56,70,88,94,102],"victims":[11],"such":[13],"activity":[14],"manifest":[15],"as":[16],"'escort":[17],"advertisements'":[18],"on":[19,85],"various":[20],"online":[21],"forums.":[22],"Given":[23],"the":[24,86],"large,":[25],"heterogeneous":[26],"noisy":[28],"structure":[29],"this":[31,45,65,76,89],"data,":[32],"building":[33],"models":[34],"to":[35,61,78],"predict":[36],"instances":[37],"convoluted":[42],"task.":[43],"In":[44],"paper":[46],"we":[47],"propose":[48],"an":[49],"entity":[50],"resolution":[51],"pipeline":[52,77],"using":[53],"notion":[55],"proxy":[57],"labels,":[58],"in":[59,92],"order":[60],"extract":[62],"clusters":[63],"from":[64,81],"data":[66],"with":[67],"prior":[68],"history":[69],"human":[71],"activity.":[73],"We":[74],"apply":[75],"5M":[79],"records":[80],"backpage.com":[82],"report":[84],"performance":[87],"approach,":[90],"challenges":[91],"terms":[93],"scalability,":[95],"some":[97],"significant":[98],"domain":[99],"specific":[100],"characteristics":[101],"our":[103],"resolved":[104],"entities.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}