{"id":"https://openalex.org/W2760277945","doi":"https://doi.org/10.18653/v1/d17-1204","title":"Finding Patterns in Noisy Crowds: Regression-based Annotation Aggregation for Crowdsourced Data","display_name":"Finding Patterns in Noisy Crowds: Regression-based Annotation Aggregation for Crowdsourced Data","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2760277945","doi":"https://doi.org/10.18653/v1/d17-1204","mag":"2760277945"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1204","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1204","pdf_url":"https://www.aclweb.org/anthology/D17-1204.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1204.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017082574","display_name":"Natalie Parde","orcid":"https://orcid.org/0000-0003-0072-7499"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natalie Parde","raw_affiliation_strings":["Department of Computer Science and Engineering University of North Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of North Texas","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089984025","display_name":"Rodney D. Nielsen","orcid":null},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rodney Nielsen","raw_affiliation_strings":["Department of Computer Science and Engineering University of North Texas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering University of North Texas","institution_ids":["https://openalex.org/I123534392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123534392"],"apc_list":null,"apc_paid":null,"fwci":2.3054,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89020071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1907","last_page":"1912"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9812999963760376,"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":0.9743000268936157,"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/crowdsourcing","display_name":"Crowdsourcing","score":0.9007288217544556},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8267284631729126},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.7292789816856384},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6673310399055481},{"id":"https://openalex.org/keywords/crowds","display_name":"Crowds","score":0.592155396938324},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5219751596450806},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5177980661392212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46971243619918823},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4302247166633606},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3427504897117615},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.12409895658493042}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.9007288217544556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267284631729126},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.7292789816856384},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6673310399055481},{"id":"https://openalex.org/C2777852691","wikidata":"https://www.wikidata.org/wiki/Q13430821","display_name":"Crowds","level":2,"score":0.592155396938324},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5219751596450806},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5177980661392212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46971243619918823},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4302247166633606},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3427504897117615},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.12409895658493042},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/d17-1204","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1204","pdf_url":"https://www.aclweb.org/anthology/D17-1204.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:info:ark/67531/metadc1042611","is_oa":false,"landing_page_url":"https://digital.library.unt.edu/ark:/67531/metadc1042611/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400792","display_name":"University of North Texas Digital Library (University of North Texas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123534392","host_organization_name":"University of North Texas","host_organization_lineage":["https://openalex.org/I123534392"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2017 Conference on Empirical Methods in Natural Language Processing, September 7-11, 2017. Copenhagen, Denmark","raw_type":"Paper"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1204","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1204","pdf_url":"https://www.aclweb.org/anthology/D17-1204.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 2017 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2354155809","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"1144248","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7128583105","display_name":"SHB: Large: Collaborative Research: Companionbots for Proactive Therapeutic Dialog on Depression","funder_award_id":"1262860","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2760277945.pdf","grobid_xml":"https://content.openalex.org/works/W2760277945.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W1570448133","https://openalex.org/W1617082848","https://openalex.org/W1970381522","https://openalex.org/W2113242816","https://openalex.org/W2129345386","https://openalex.org/W2134305421","https://openalex.org/W2140890285","https://openalex.org/W2250244475","https://openalex.org/W2250854390","https://openalex.org/W2251054028","https://openalex.org/W2251818274","https://openalex.org/W2575687710","https://openalex.org/W2761817502"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4318823662","https://openalex.org/W3207526114"],"abstract_inverted_index":{"Crowdsourcing":[0],"offers":[1],"a":[2,35,56],"convenient":[3],"means":[4],"of":[5,58],"obtaining":[6],"labeled":[7],"data":[8],"quickly":[9],"and":[10],"inexpensively.":[11],"However,":[12],"crowdsourced":[13,39],"labels":[14,44,54,62],"are":[15],"often":[16],"noisier":[17],"than":[18],"expert-annotated":[19],"data,":[20,65],"making":[21],"it":[22],"difficult":[23],"to":[24,41],"aggregate":[25],"them":[26],"meaningfully.":[27],"We":[28],"present":[29],"an":[30],"aggregation":[31,70],"approach":[32,75],"that":[33,47],"learns":[34],"regression":[36],"model":[37],"from":[38],"annotations":[40],"predict":[42],"aggregated":[43],"for":[45],"instances":[46],"have":[48],"no":[49],"expert":[50,61],"adjudications.":[51],"The":[52],"predicted":[53],"achieve":[55],"correlation":[57],"0.594":[59],"with":[60],"on":[63,80],"our":[64],"outperforming":[66],"the":[67,78],"best":[68],"alternative":[69],"method":[71],"by":[72],"11.9%.":[73],"Our":[74],"also":[76],"outperforms":[77],"alternatives":[79],"third-party":[81],"datasets.":[82]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}