{"id":"https://openalex.org/W4303427073","doi":"https://doi.org/10.1145/3567419","title":"A Data-Driven Analysis of Behaviors in Data Curation Processes","display_name":"A Data-Driven Analysis of Behaviors in Data Curation Processes","publication_year":2022,"publication_date":"2022-10-07","ids":{"openalex":"https://openalex.org/W4303427073","doi":"https://doi.org/10.1145/3567419"},"language":"en","primary_location":{"id":"doi:10.1145/3567419","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3567419","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","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/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":true,"raw_author_name":"Lei Han","raw_affiliation_strings":["The University of Queensland, Australia"],"affiliations":[{"raw_affiliation_string":"The University of 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":["The University of Queensland, Australia"],"affiliations":[{"raw_affiliation_string":"The University of 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":["The University of Queensland, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019857678","display_name":"Marta Indulska","orcid":"https://orcid.org/0000-0002-2156-4097"},"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":"Marta Indulska","raw_affiliation_strings":["The University of Queensland, Australia"],"affiliations":[{"raw_affiliation_string":"The University of 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":["The University of Queensland, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Queensland, Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101540918"],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":0.8184,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75282936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"41","issue":"3","first_page":"1","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9977999925613403,"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":0.9977999925613403,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9936000108718872,"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"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.843611478805542},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7155612707138062},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5427179336547852},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5413389801979065},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5199969410896301},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49413445591926575},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4257936179637909},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42199257016181946},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3643600344657898},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08361843228340149}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.843611478805542},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7155612707138062},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5427179336547852},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5413389801979065},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5199969410896301},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49413445591926575},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4257936179637909},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42199257016181946},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3643600344657898},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08361843228340149},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3567419","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3567419","pdf_url":null,"source":{"id":"https://openalex.org/S4394735545","display_name":"ACM Transactions on Information Systems","issn_l":"1046-8188","issn":["1046-8188","1558-2868"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1610496399","https://openalex.org/W1972978214","https://openalex.org/W1991079201","https://openalex.org/W2006291142","https://openalex.org/W2057559934","https://openalex.org/W2058751521","https://openalex.org/W2064766209","https://openalex.org/W2079262584","https://openalex.org/W2125027820","https://openalex.org/W2134504514","https://openalex.org/W2151905266","https://openalex.org/W2151996389","https://openalex.org/W2166687274","https://openalex.org/W2249254870","https://openalex.org/W2270249641","https://openalex.org/W2294546257","https://openalex.org/W2417029388","https://openalex.org/W2562283110","https://openalex.org/W2612957914","https://openalex.org/W2783539613","https://openalex.org/W2792572948","https://openalex.org/W2810627707","https://openalex.org/W2911529586","https://openalex.org/W2914783728","https://openalex.org/W2920914241","https://openalex.org/W2922012916","https://openalex.org/W3011590361","https://openalex.org/W3012094108","https://openalex.org/W3029367893","https://openalex.org/W3035376455","https://openalex.org/W3096972338","https://openalex.org/W3118813946","https://openalex.org/W4213346165","https://openalex.org/W4238202281","https://openalex.org/W4247854836","https://openalex.org/W4249448758","https://openalex.org/W4249744258","https://openalex.org/W4251720056","https://openalex.org/W6636177537"],"related_works":["https://openalex.org/W2140798747","https://openalex.org/W2948169060","https://openalex.org/W2730112582","https://openalex.org/W2358580169","https://openalex.org/W2111347279","https://openalex.org/W2110696645","https://openalex.org/W2487211728","https://openalex.org/W2378096925","https://openalex.org/W2912415823","https://openalex.org/W3005557527"],"abstract_inverted_index":{"Understanding":[0],"how":[1,98],"data":[2,14,43,49,59,63,75,79,209,219,229,289,328,337,341],"workers":[3,44,76,210,290],"interact":[4],"with":[5,126,213,319],"data,":[6],"and":[7,67,171,178,216,261,291,323,335],"various":[8,320],"pieces":[9],"of":[10,36,74,123,133,165,317],"information":[11,324],"related":[12],"to":[13,18,69,103,150,192,224,233,253,262,267,279,294],"preparation,":[15],"is":[16,33,143,184,220],"key":[17],"designing":[19],"systems":[20],"that":[21,118,188,200,240,245],"can":[22,89,173,189,207],"better":[23,194,296],"support":[24,225],"them":[25,293],"in":[26,77,155,181,256,303],"exploring":[27],"datasets.":[28],"To":[29,106],"date,":[30],"however,":[31],"there":[32],"a":[34,57,111,115,127,144,159,185,276],"paucity":[35],"research":[37],"studying":[38],"the":[39,72,121,163,205,241,251,282,299,304],"strategies":[40],"adopted":[41],"by":[42,288],"as":[45,93,95],"they":[46],"carry":[47],"out":[48],"preparation":[50,60],"activities.":[51],"In":[52],"this":[53,107],"work,":[54],"we":[55,109,237,274],"investigate":[56],"specific":[58],"activity,":[61],"namely":[62],"quality":[64,80,164],"discovery":[65],",":[66],"aim":[68],"(i)":[70,141],"understand":[71,97],"behaviors":[73,231],"discovering":[78],"issues,":[81],"(ii)":[82,153],"explore":[83],"what":[84],"factors":[85],"(e.g.,":[86],"prior":[87,232],"experience)":[88],"affect":[90],"their":[91,104,214],"behaviors,":[92],"well":[94],"(iii)":[96,179],"these":[99],"behavioral":[100],"observations":[101],"relate":[102],"performance.":[105,195],"end,":[108],"collect":[110],"multi-modal":[112],"dataset":[113],"through":[114,340],"data-driven":[116],"experiment":[117,137,198,272],"relies":[119],"on":[120,131,162,270],"use":[122],"eye-tracking":[124],"technology":[125],"purpose-designed":[128],"platform":[129],"built":[130],"top":[132,283],"iPython":[134],"Notebook.":[135],"The":[136],"results":[138],"reveal":[139],"that:":[140],"\u2018copy\u2013paste\u2013modify\u2019":[142],"typical":[145],"strategy":[146],"for":[147,264],"writing":[148,156,257],"code":[149,157,203,260,266,285],"complete":[151],"tasks;":[152],"proficiency":[154],"has":[158],"significant":[160],"impact":[161],"task":[166,175],"performance,":[167],"while":[168],"perceived":[169],"difficulty":[170],"efficacy":[172],"influence":[174],"completion":[176],"patterns;":[177],"searching":[180],"external":[182,247],"resources":[183,325],"prevalent":[186],"action":[187],"be":[190],"leveraged":[191],"achieve":[193,295],"Furthermore,":[196],"our":[197,271,309],"indicates":[199],"providing":[201],"sample":[202],"within":[204],"system":[206,321],"help":[208],"get":[211],"started":[212],"task,":[215],"surfacing":[217],"underlying":[218],"an":[221],"effective":[222,334],"way":[223],"exploration.":[226],"By":[227,306],"investigating":[228],"worker":[230],"each":[234],"search":[235,248,263],"action,":[236],"also":[238,332],"find":[239],"most":[242],"common":[243],"reasons":[244],"trigger":[246],"actions":[249],"are":[250],"need":[252],"seek":[254],"assistance":[255],"or":[258],"debugging":[259],"relevant":[265],"reuse.":[268],"Based":[269],"results,":[273],"showcase":[275],"systematic":[277],"approach":[278],"select":[280],"from":[281],"best":[284,300],"snippets":[286],"created":[287],"assemble":[292],"performance":[297],"than":[298],"individual":[301],"performer":[302],"dataset.":[305],"doing":[307],"so,":[308],"findings":[310],"not":[311],"only":[312],"provide":[313],"insights":[314],"into":[315],"patterns":[316],"interactions":[318],"components":[322],"when":[326],"performing":[327],"curation":[329,338],"tasks,":[330],"but":[331],"build":[333],"efficient":[336],"processes":[339],"workers\u2019":[342],"collective":[343],"intelligence.":[344]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
