{"id":"https://openalex.org/W4392223038","doi":"https://doi.org/10.1145/3613904.3642834","title":"If in a Crowdsourced Data Annotation Pipeline, a GPT-4","display_name":"If in a Crowdsourced Data Annotation Pipeline, a GPT-4","publication_year":2024,"publication_date":"2024-05-11","ids":{"openalex":"https://openalex.org/W4392223038","doi":"https://doi.org/10.1145/3613904.3642834"},"language":"en","primary_location":{"id":"doi:10.1145/3613904.3642834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642834","pdf_url":null,"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 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3613904.3642834","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101817568","display_name":"Zeyu He","orcid":"https://orcid.org/0009-0007-7115-2692"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu He","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, United States"],"raw_orcid":"https://orcid.org/0009-0007-7115-2692","affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102729368","display_name":"Chieh-Yang Huang","orcid":"https://orcid.org/0009-0001-6736-9959"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chieh-Yang Huang","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, United States"],"raw_orcid":"https://orcid.org/0009-0001-6736-9959","affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023951721","display_name":"Chien\u2010Kuang Cornelia Ding","orcid":"https://orcid.org/0000-0001-9047-0222"},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chien-Kuang Cornelia Ding","raw_affiliation_strings":["Pathology, University of California, San Francisco, United States"],"raw_orcid":"https://orcid.org/0000-0001-9047-0222","affiliations":[{"raw_affiliation_string":"Pathology, University of California, San Francisco, United States","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045452927","display_name":"Shaurya Rohatgi","orcid":"https://orcid.org/0000-0001-7426-4576"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaurya Rohatgi","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, United States"],"raw_orcid":"https://orcid.org/0000-0001-7426-4576","affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, United States","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083675499","display_name":"Ting-Hao Huang","orcid":"https://orcid.org/0000-0001-7021-4627"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting-Hao Kenneth Huang","raw_affiliation_strings":["College of Information Sciences and Technology, Pennsylvania State University, United States"],"raw_orcid":"https://orcid.org/0000-0001-7021-4627","affiliations":[{"raw_affiliation_string":"College of Information Sciences and Technology, Pennsylvania State University, United States","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.4934,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.9903125,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"25"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9933000206947327,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9695000052452087,"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":0.93551105260849},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.8467906713485718},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7159745097160339},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.641803503036499},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5320136547088623},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.49400025606155396},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.481035053730011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.365240216255188},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3523998260498047},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3500858545303345},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21596243977546692},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08305701613426208}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.93551105260849},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8467906713485718},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7159745097160339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.641803503036499},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5320136547088623},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.49400025606155396},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.481035053730011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.365240216255188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3523998260498047},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3500858545303345},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21596243977546692},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08305701613426208},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3613904.3642834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642834","pdf_url":null,"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 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2402.16795","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.16795","pdf_url":"https://arxiv.org/pdf/2402.16795","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3613904.3642834","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613904.3642834","pdf_url":null,"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 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W1141062540","https://openalex.org/W1541075651","https://openalex.org/W1565732937","https://openalex.org/W1996878936","https://openalex.org/W2058738785","https://openalex.org/W2070248097","https://openalex.org/W2134305421","https://openalex.org/W2137244916","https://openalex.org/W2163471296","https://openalex.org/W2469104253","https://openalex.org/W2585226541","https://openalex.org/W2767941892","https://openalex.org/W2792932412","https://openalex.org/W2799915114","https://openalex.org/W2810233980","https://openalex.org/W2898725686","https://openalex.org/W3012845547","https://openalex.org/W3094235867","https://openalex.org/W3111114607","https://openalex.org/W3163443091","https://openalex.org/W3169215920","https://openalex.org/W3175362313","https://openalex.org/W3205769026","https://openalex.org/W4205737716","https://openalex.org/W4220891329","https://openalex.org/W4283168936","https://openalex.org/W4292341621","https://openalex.org/W4327811957","https://openalex.org/W4392903699"],"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/W1570025324","https://openalex.org/W2116902754","https://openalex.org/W2166185180"],"abstract_inverted_index":{"Recent":[0],"studies":[1,21],"indicated":[2],"GPT-4":[3,43,99],"outperforms":[4],"online":[5],"crowd":[6,108],"workers":[7,13,53],"in":[8],"data":[9],"labeling":[10,54,140,148],"accuracy,":[11],"notably":[12],"from":[14,26,58],"Amazon":[15],"Mechanical":[16],"Turk":[17],"(MTurk).":[18],"However,":[19],"these":[20],"were":[22,73],"criticized":[23],"for":[24,116],"deviating":[25],"standard":[27],"crowdsourcing":[28],"practices":[29],"and":[30,44,47,138],"emphasizing":[31],"individual":[32],"workers\u2019":[33],"performances":[34],"over":[35],"the":[36,63,78,121,136],"whole":[37],"data-annotation":[38],"process.":[39],"This":[40],"paper":[41],"compared":[42],"an":[45,112,125],"ethical":[46],"well-executed":[48],"MTurk":[49,92],"pipeline,":[50],"with":[51,107],"415":[52],"3,177":[55],"sentence":[56],"segments":[57],"200":[59],"scholarly":[60],"articles":[61],"using":[62],"CODA-19":[64],"scheme.":[65],"Two":[66],"worker":[67,114],"interfaces":[68],"yielded":[69],"127,080":[70],"labels,":[71],"which":[72],"then":[74],"used":[75],"to":[76],"infer":[77],"final":[79],"labels":[80,106,109],"through":[81],"eight":[82],"label-aggregation":[83],"algorithms.":[84],"Our":[85],"evaluation":[86],"showed":[87],"that":[88],"despite":[89],"best":[90],"practices,":[91],"pipeline\u2019s":[93],"highest":[94],"accuracy":[95,128],"was":[96],"81.5%,":[97],"whereas":[98],"achieved":[100,124],"83.6%.":[101],"Interestingly,":[102],"when":[103,135],"combining":[104],"GPT-4\u2019s":[105,139],"collected":[110],"via":[111],"advanced":[113],"interface":[115],"aggregation,":[117],"2":[118],"out":[119],"of":[120],"8":[122],"algorithms":[123],"even":[126],"higher":[127],"(87.5%,":[129],"87.0%).":[130],"Further":[131],"analysis":[132],"suggested":[133],"that,":[134],"crowd\u2019s":[137],"strengths":[141],"are":[142],"complementary,":[143],"aggregating":[144],"them":[145],"could":[146],"increase":[147],"accuracy.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":5}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}