{"id":"https://openalex.org/W4212966400","doi":"https://doi.org/10.1109/tkde.2022.3151605","title":"DataOps-4G: On Supporting Generalists in Data Quality Discovery","display_name":"DataOps-4G: On Supporting Generalists in Data Quality Discovery","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4212966400","doi":"https://doi.org/10.1109/tkde.2022.3151605"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2022.3151605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3151605","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033215704","display_name":"Shaochen Yu","orcid":"https://orcid.org/0000-0002-4526-1525"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Shaochen Yu","raw_affiliation_strings":["School of ITEE, The University of Queensland, 1974 Saint Lucia, Queensland, Australia,"],"affiliations":[{"raw_affiliation_string":"School of ITEE, The University of Queensland, 1974 Saint Lucia, Queensland, Australia,","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044462112","display_name":"Tianwa Chen","orcid":"https://orcid.org/0000-0002-5135-0313"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tianwa Chen","raw_affiliation_strings":["School of ITEE, The University of Queensland, 1974 Saint Lucia, Queensland, Australia,"],"affiliations":[{"raw_affiliation_string":"School of ITEE, The University of Queensland, 1974 Saint Lucia, Queensland, Australia,","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101540918","display_name":"Lei Han","orcid":"https://orcid.org/0000-0002-7777-3592"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lei Han","raw_affiliation_strings":["School of ITEE, University of Queensland, 1974 Brisbane, Queensland, Australia,"],"affiliations":[{"raw_affiliation_string":"School of ITEE, University of Queensland, 1974 Brisbane, Queensland, Australia,","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052565959","display_name":"Gianluca Demartini","orcid":"https://orcid.org/0000-0002-7311-3693"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gianluca Demartini","raw_affiliation_strings":["School of ITEE, The University of Queensland, 1974 Saint Lucia, Queensland, Australia,"],"affiliations":[{"raw_affiliation_string":"School of ITEE, The University of Queensland, 1974 Saint Lucia, Queensland, Australia,","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070591850","display_name":"Shazia Sadiq","orcid":"https://orcid.org/0000-0001-6739-4145"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shazia Sadiq","raw_affiliation_strings":["School of ITEE, The University of Queensland, Brisbane, Queensland, Australia,"],"affiliations":[{"raw_affiliation_string":"School of ITEE, The University of Queensland, Brisbane, Queensland, Australia,","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033215704"],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":0.6546,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6993317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9976999759674072,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8665668964385986},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.7926424741744995},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.7055673599243164},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6474658846855164},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.6011950969696045},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5896088480949402},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.51636803150177},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5126318335533142},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42685556411743164},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4160900115966797},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32372015714645386},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.30322420597076416},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.1136813759803772}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8665668964385986},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7926424741744995},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.7055673599243164},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6474658846855164},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.6011950969696045},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5896088480949402},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.51636803150177},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5126318335533142},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42685556411743164},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4160900115966797},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32372015714645386},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.30322420597076416},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.1136813759803772},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2022.3151605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2022.3151605","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.6299999952316284}],"awards":[{"id":"https://openalex.org/G2377593808","display_name":null,"funder_award_id":"DP190102141","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1560431099","https://openalex.org/W1689950805","https://openalex.org/W1972978214","https://openalex.org/W1991079201","https://openalex.org/W1992479406","https://openalex.org/W1997927541","https://openalex.org/W2046298800","https://openalex.org/W2047607378","https://openalex.org/W2048498434","https://openalex.org/W2053062910","https://openalex.org/W2064766209","https://openalex.org/W2075811803","https://openalex.org/W2093044076","https://openalex.org/W2106817091","https://openalex.org/W2128118880","https://openalex.org/W2132290529","https://openalex.org/W2132525863","https://openalex.org/W2133160781","https://openalex.org/W2139531859","https://openalex.org/W2240592568","https://openalex.org/W2368635037","https://openalex.org/W2417029388","https://openalex.org/W2421097601","https://openalex.org/W2544486974","https://openalex.org/W2604226652","https://openalex.org/W2792572948","https://openalex.org/W2798649495","https://openalex.org/W2805752465","https://openalex.org/W2809161078","https://openalex.org/W2941766203","https://openalex.org/W3035376455","https://openalex.org/W3081548510","https://openalex.org/W3090546698","https://openalex.org/W3103621440","https://openalex.org/W4213251304","https://openalex.org/W4240301789","https://openalex.org/W6639113821","https://openalex.org/W6676014748","https://openalex.org/W6755142466"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W1503094549","https://openalex.org/W4384486036","https://openalex.org/W135177976","https://openalex.org/W3081133439","https://openalex.org/W2889043750","https://openalex.org/W4386246791","https://openalex.org/W3211701140","https://openalex.org/W2952280724","https://openalex.org/W2133103607"],"abstract_inverted_index":{"Data":[0],"preparation":[1,36],"has":[2],"become":[3],"a":[4,33,75,118],"necessary":[5],"but":[6],"labor":[7],"and":[8,55,64,108,140,145,156,166,185],"resource":[9],"intensive":[10],"step":[11],"to":[12,84,91,104,122,189],"perform":[13],"data":[14,35,39,48,51,67,76,87,106,175],"analytics.":[15],"To":[16,69],"date,":[17],"such":[18],"activities":[19,194],"still":[20],"require":[21],"considerable":[22],"manual":[23],"effort":[24,144],"from":[25,127,182],"experts.":[26],"In":[27],"this":[28,70],"paper,":[29],"we":[30,72,116],"focus":[31,190],"on":[32,191],"specific":[34],"activity,":[37],"namely":[38],"quality":[40,52,107],"discovery.":[41],"We":[42,94],"explore":[43,105],"different":[44],"settings":[45,60],"in":[46,147],"which":[47],"workers":[49],"undertake":[50],"discovery":[53],"tasks":[54],"the":[56,62,89,110,132,135,171],"implications":[57],"of":[58,66,134,173],"those":[59],"for":[61,79],"efficiency":[63,157],"effectiveness":[65,155],"workers.":[68],"end,":[71],"propose":[73],"DataOps-4G,":[74],"curation":[77,176],"platform":[78,126],"generalists,":[80],"that":[81,100],"allows":[82],"users":[83],"interact":[85],"with":[86],"without":[88],"need":[90],"write":[92],"code.":[93],"wrap":[95],"up":[96,170],"pre-defined":[97],"code":[98,111],"snippets":[99],"implement":[101],"useful":[102],"functionalities":[103],"bundle":[109],"into":[112],"so-called":[113],"DataOps.":[114],"Then,":[115],"conduct":[117],"lab-based":[119],"user":[120],"study":[121],"evaluate":[123],"our":[124],"DataOps-4G":[125],"two":[128],"perspectives:":[129],"(i)":[130],"effectiveness,":[131],"accuracy":[133],"outcomes":[136],"achieved":[137],"by":[138,161,178],"participants;":[139],"(ii)":[141],"efficiency,":[142],"their":[143,162],"strategies":[146],"task":[148,163],"completion.":[149],"Our":[150],"experimental":[151],"results":[152],"uncover":[153],"how":[154],"can":[158],"be":[159],"affected":[160],"completion":[164],"patterns":[165],"strategies.":[167],"This":[168],"opens":[169],"possibility":[172],"popularizing":[174],"processes":[177],"employing":[179],"non-experts":[180],"(e.g.,":[181,195],"crowdsourcing":[183],"platforms)":[184],"consequently":[186],"allowing":[187],"experts":[188],"more":[192],"complex":[193],"building":[196],"machine":[197],"learning":[198],"models).":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
