{"id":"https://openalex.org/W2132667707","doi":"https://doi.org/10.1145/2047196.2047205","title":"Proactive wrangling","display_name":"Proactive wrangling","publication_year":2011,"publication_date":"2011-10-16","ids":{"openalex":"https://openalex.org/W2132667707","doi":"https://doi.org/10.1145/2047196.2047205","mag":"2132667707"},"language":"en","primary_location":{"id":"doi:10.1145/2047196.2047205","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2047196.2047205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th annual ACM symposium on User interface software and technology","raw_type":"proceedings-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/A5060695800","display_name":"Philip J. Guo","orcid":"https://orcid.org/0000-0002-4579-5754"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Philip J. Guo","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111792512","display_name":"Sean Kandel","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sean Kandel","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043626252","display_name":"Joseph M. Hellerstein","orcid":"https://orcid.org/0000-0002-7712-4306"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph M. Hellerstein","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090570042","display_name":"Jeffrey Heer","orcid":"https://orcid.org/0000-0002-6175-1655"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Heer","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060695800"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":5.3512,"has_fulltext":false,"cited_by_count":109,"citation_normalized_percentile":{"value":0.95637828,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9948999881744385,"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":0.772371768951416},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6857367753982544},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.5373380184173584},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.518242359161377},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5098006129264832},{"id":"https://openalex.org/keywords/model-transformation","display_name":"Model transformation","score":0.448769748210907},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.42088431119918823},{"id":"https://openalex.org/keywords/homogeneity","display_name":"Homogeneity (statistics)","score":0.4168555438518524},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.413134902715683},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4124095141887665},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38984230160713196},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3333684206008911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1966162919998169},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.18769577145576477},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1459694802761078},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14190003275871277}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772371768951416},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6857367753982544},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.5373380184173584},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.518242359161377},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5098006129264832},{"id":"https://openalex.org/C2779791154","wikidata":"https://www.wikidata.org/wiki/Q258040","display_name":"Model transformation","level":3,"score":0.448769748210907},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.42088431119918823},{"id":"https://openalex.org/C142259097","wikidata":"https://www.wikidata.org/wiki/Q5891314","display_name":"Homogeneity (statistics)","level":2,"score":0.4168555438518524},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.413134902715683},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4124095141887665},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38984230160713196},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3333684206008911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1966162919998169},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.18769577145576477},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1459694802761078},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14190003275871277},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2047196.2047205","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2047196.2047205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th annual ACM symposium on User interface software and technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1492324553","https://openalex.org/W1551385575","https://openalex.org/W1984315811","https://openalex.org/W1994053659","https://openalex.org/W1997533292","https://openalex.org/W2014596857","https://openalex.org/W2054974985","https://openalex.org/W2059216172","https://openalex.org/W2064766209","https://openalex.org/W2086679600","https://openalex.org/W2087634802","https://openalex.org/W2102480769","https://openalex.org/W2106895292","https://openalex.org/W2121932026","https://openalex.org/W2123390832","https://openalex.org/W2132525863","https://openalex.org/W2149263361","https://openalex.org/W2151763080","https://openalex.org/W2163314677","https://openalex.org/W2164611950","https://openalex.org/W2913602672","https://openalex.org/W4233189519","https://openalex.org/W4237412827","https://openalex.org/W4250102289","https://openalex.org/W4255149377"],"related_works":["https://openalex.org/W2365767001","https://openalex.org/W2612824201","https://openalex.org/W2111829026","https://openalex.org/W2083001816","https://openalex.org/W811092902","https://openalex.org/W1605273124","https://openalex.org/W2372774066","https://openalex.org/W2147311558","https://openalex.org/W1978492080","https://openalex.org/W2062952062"],"abstract_inverted_index":{"Analysts":[0],"regularly":[1],"wrangle":[2],"data":[3,25,50,55],"into":[4],"a":[5,12,36,45,57,74],"form":[6],"suitable":[7],"for":[8,153],"computational":[9],"tools":[10,22],"through":[11,67],"tedious":[13],"process":[14],"that":[15,76,120,132],"delays":[16],"more":[17],"substantive":[18],"analysis.":[19],"While":[20],"interactive":[21],"can":[23,126],"assist":[24,127],"transformation,":[26],"analysts":[27],"must":[28],"still":[29],"conceptualize":[30],"the":[31,68,85,101,107,114,144],"desired":[32],"output":[33],"state,":[34],"formulate":[35],"transformation":[37,129],"strategy,":[38],"and":[39,84],"specify":[40],"complex":[41],"transforms.":[42],"We":[43,146],"present":[44],"model":[46,96,125],"to":[47,56,80,91,142],"proactively":[48],"suggest":[49],"transforms":[51],"which":[52],"map":[53],"input":[54],"relational":[58],"format":[59],"expected":[60],"by":[61,123],"analysis":[62],"tools.":[63],"To":[64],"guide":[65],"search":[66],"space":[69],"of":[70,87,100,113,150],"transforms,":[71],"we":[72],"propose":[73],"metric":[75],"scores":[77],"tables":[78],"according":[79],"type":[81],"homogeneity,":[82],"sparsity":[83],"presence":[86],"delimiters.":[88],"When":[89],"compared":[90],"\"ideal\"":[92],"hand-crafted":[93],"transformations,":[94],"our":[95,124],"suggests":[97],"over":[98],"half":[99],"needed":[102],"steps;":[103],"in":[104],"these":[105,151],"cases":[106],"top-ranked":[108],"suggestion":[109],"is":[110],"preferred":[111],"77%":[112],"time.":[115],"User":[116],"study":[117],"results":[118,152],"indicate":[119],"suggestions":[121],"produced":[122],"analysts'":[128],"tasks,":[130],"but":[131],"users":[133],"do":[134],"not":[135],"always":[136],"value":[137],"proactive":[138],"assistance,":[139],"instead":[140],"preferring":[141],"maintain":[143],"initiative.":[145],"discuss":[147],"some":[148],"implications":[149],"mixed-initiative":[154],"interfaces.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}