{"id":"https://openalex.org/W4282813546","doi":"https://doi.org/10.1145/3531146.3533175","title":"Smallset Timelines: A Visual Representation of Data Preprocessing Decisions","display_name":"Smallset Timelines: A Visual Representation of Data Preprocessing Decisions","publication_year":2022,"publication_date":"2022-06-20","ids":{"openalex":"https://openalex.org/W4282813546","doi":"https://doi.org/10.1145/3531146.3533175"},"language":"en","primary_location":{"id":"doi:10.1145/3531146.3533175","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3531146.3533175","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3531146.3533175","source":{"id":"https://openalex.org/S4363608463","display_name":"2022 ACM Conference on Fairness, Accountability, and Transparency","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3531146.3533175","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037258144","display_name":"Lydia R Lucchesi","orcid":"https://orcid.org/0000-0002-1901-4301"},"institutions":[{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Lydia R. Lucchesi","raw_affiliation_strings":["Australian National University, Australia and CSIRO's Data61, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Australia and CSIRO's Data61, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679","https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055776500","display_name":"Petra Kuhnert","orcid":"https://orcid.org/0000-0001-9070-0091"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]},{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Petra M. Kuhnert","raw_affiliation_strings":["CSIRO's Data61, Australia and Australian National University, Australia"],"affiliations":[{"raw_affiliation_string":"CSIRO's Data61, Australia and Australian National University, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679","https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101606112","display_name":"Jenny L. Davis","orcid":"https://orcid.org/0000-0003-0952-5842"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jenny L. Davis","raw_affiliation_strings":["Australian National University, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049449495","display_name":"Lexing Xie","orcid":"https://orcid.org/0000-0001-8319-0118"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lexing Xie","raw_affiliation_strings":["Australian National University, Australia and CSIRO's Data61, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Australia and CSIRO's Data61, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679","https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037258144"],"corresponding_institution_ids":["https://openalex.org/I118347636","https://openalex.org/I1292875679","https://openalex.org/I42894916"],"apc_list":null,"apc_paid":null,"fwci":1.678,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.89284187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1136","last_page":"1153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9988999962806702,"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/T14280","display_name":"Big Data Technologies and Applications","score":0.9843999743461609,"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"}},{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/timeline","display_name":"Timeline","score":0.9192931652069092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7800499796867371},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6835589408874512},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6628923416137695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42937609553337097},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40801575779914856},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.371107280254364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09290331602096558},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08815979957580566}],"concepts":[{"id":"https://openalex.org/C4438859","wikidata":"https://www.wikidata.org/wiki/Q186117","display_name":"Timeline","level":2,"score":0.9192931652069092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800499796867371},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6835589408874512},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6628923416137695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42937609553337097},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40801575779914856},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.371107280254364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09290331602096558},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08815979957580566},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3531146.3533175","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3531146.3533175","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3531146.3533175","source":{"id":"https://openalex.org/S4363608463","display_name":"2022 ACM Conference on Fairness, Accountability, and Transparency","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3531146.3533175","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3531146.3533175","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3531146.3533175","source":{"id":"https://openalex.org/S4363608463","display_name":"2022 ACM Conference on Fairness, Accountability, and Transparency","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 ACM Conference on Fairness Accountability and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"No poverty","score":0.75,"id":"https://metadata.un.org/sdg/1"}],"awards":[{"id":"https://openalex.org/G4166859443","display_name":null,"funder_award_id":"DP180101985","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320320386","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4282813546.pdf","grobid_xml":"https://content.openalex.org/works/W4282813546.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W92977396","https://openalex.org/W1899647947","https://openalex.org/W2023338600","https://openalex.org/W2097883090","https://openalex.org/W2100960835","https://openalex.org/W2126626812","https://openalex.org/W2145154883","https://openalex.org/W2395429379","https://openalex.org/W2526501380","https://openalex.org/W2588064451","https://openalex.org/W2593083061","https://openalex.org/W2753739212","https://openalex.org/W2897042519","https://openalex.org/W2911227954","https://openalex.org/W2963917042","https://openalex.org/W2973366514","https://openalex.org/W2974071289","https://openalex.org/W2997591727","https://openalex.org/W3012210082","https://openalex.org/W3073969270","https://openalex.org/W3092626593","https://openalex.org/W3092896626","https://openalex.org/W3098953614","https://openalex.org/W3100279624","https://openalex.org/W3125733373","https://openalex.org/W3133631714","https://openalex.org/W3135371071","https://openalex.org/W3159054342","https://openalex.org/W3174365296","https://openalex.org/W3189849087","https://openalex.org/W3207830467","https://openalex.org/W3212368439","https://openalex.org/W4235791242","https://openalex.org/W4288083800","https://openalex.org/W4372046852"],"related_works":["https://openalex.org/W1858249912","https://openalex.org/W2114034199","https://openalex.org/W4391249598","https://openalex.org/W2317428717","https://openalex.org/W2734259032","https://openalex.org/W3094038556","https://openalex.org/W2014772881","https://openalex.org/W4254228154","https://openalex.org/W4296345146","https://openalex.org/W2952736244"],"abstract_inverted_index":{"Data":[0],"preprocessing":[1,46,77,117,161,176,205],"is":[2,24,50,67],"a":[3,37,51,142,194],"crucial":[4],"stage":[5,78],"in":[6,27,75,174,185],"the":[7,20,34,57,76,83,94,102,120,138,156],"data":[8,45,116,168,180,196],"analysis":[9],"pipeline,":[10],"with":[11,98],"both":[12],"technical":[13],"and":[14,30,43,79,91,114,127,169,182,202],"social":[15],"aspects":[16],"to":[17,39,81,93,124,136,141,152],"consider.":[18],"Yet,":[19],"attention":[21],"it":[22,134],"receives":[23],"often":[25],"lacking":[26],"research":[28],"practice":[29],"dissemination.":[31],"We":[32,100,147,189],"present":[33,148],"Smallset":[35,70,110,157,191],"Timeline,":[36],"visualisation":[38],"help":[40],"reflect":[41,125],"on":[42,126],"communicate":[44],"decisions.":[47,162],"A":[48],"\u201cSmallset\u201d":[49],"small":[52],"selection":[53],"of":[54,62,69,145,155,179,204],"rows":[55],"from":[56,112],"original":[58],"dataset":[59,63,95],"containing":[60],"instances":[61],"alterations.":[64],"The":[65],"Timeline":[66,158],"comprised":[68],"snapshots":[71],"representing":[72],"different":[73],"points":[74],"captions":[80],"describe":[82],"alterations":[84],"visualised":[85],"at":[86,207],"each":[87],"point.":[88],"Edits,":[89],"additions,":[90],"deletions":[92],"are":[96],"highlighted":[97],"colour.":[99],"develop":[101],"R":[103,113],"software":[104,166],"package,":[105],"smallsets,":[106],"that":[107],"can":[108],"create":[109],"Timelines":[111,192],"Python":[115],"scripts.":[118],"Constructing":[119],"figure":[121],"asks":[122],"practitioners":[123],"revise":[128],"decisions":[129],"as":[130,193],"necessary,":[131],"while":[132],"sharing":[133],"aims":[135],"make":[137],"process":[139],"accessible":[140],"diverse":[143],"range":[144],"audiences.":[146],"two":[149],"case":[150],"studies":[151,164],"illustrate":[153],"use":[154],"for":[159],"visualising":[160],"Case":[163],"include":[165],"defect":[167],"income":[170],"survey":[171],"benchmark":[172],"data,":[173],"which":[175],"affects":[177],"levels":[178],"loss":[181],"group":[183],"fairness":[184],"prediction":[186],"tasks,":[187],"respectively.":[188],"envision":[190],"go-to":[195],"provenance":[197],"tool,":[198],"enabling":[199],"better":[200],"documentation":[201],"communication":[203],"tasks":[206],"large.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":20}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}