{"id":"https://openalex.org/W1488337274","doi":"https://doi.org/10.1002/meet.2014.14505101138","title":"Parameter tuning: Exposing the gap between data curation and effective data analytics","display_name":"Parameter tuning: Exposing the gap between data curation and effective data analytics","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W1488337274","doi":"https://doi.org/10.1002/meet.2014.14505101138","mag":"1488337274"},"language":"en","primary_location":{"id":"doi:10.1002/meet.2014.14505101138","is_oa":false,"landing_page_url":"https://doi.org/10.1002/meet.2014.14505101138","pdf_url":null,"source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"Proceedings of the American Society for Information Science and Technology","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/A5043442839","display_name":"Catherine Blake","orcid":"https://orcid.org/0000-0001-9516-2683"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Catherine Blake","raw_affiliation_strings":["School of Library and Information Science University of Illinois at Urbana\u2010Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Library and Information Science University of Illinois at Urbana\u2010Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045275801","display_name":"Henry A. Gabb","orcid":"https://orcid.org/0000-0002-9507-4250"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Henry A. Gabb","raw_affiliation_strings":["School of Library and Information Science University of Illinois at Urbana\u2010Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Library and Information Science University of Illinois at Urbana\u2010Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043442839","https://openalex.org/A5045275801"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.8201,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80483203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"51","issue":"1","first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.9962999820709229,"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/T11937","display_name":"Research Data Management Practices","score":0.9962999820709229,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9932000041007996,"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/T13398","display_name":"Data Analysis with R","score":0.9884999990463257,"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/data-curation","display_name":"Data curation","score":0.7879965305328369},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.7746423482894897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7405675649642944},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7109329700469971},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6373400688171387},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.46366575360298157},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.45616278052330017},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.44762417674064636},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4456748962402344},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4192928671836853},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3994119167327881},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.20900416374206543}],"concepts":[{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.7879965305328369},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.7746423482894897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405675649642944},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7109329700469971},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6373400688171387},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.46366575360298157},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.45616278052330017},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44762417674064636},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4456748962402344},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4192928671836853},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3994119167327881},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.20900416374206543},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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:10.1002/meet.2014.14505101138","is_oa":false,"landing_page_url":"https://doi.org/10.1002/meet.2014.14505101138","pdf_url":null,"source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4300000071525574,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1494137514","https://openalex.org/W1548849615","https://openalex.org/W1605275907","https://openalex.org/W1995459592","https://openalex.org/W2033626294","https://openalex.org/W2111322878","https://openalex.org/W2157583440","https://openalex.org/W2435251607","https://openalex.org/W2620485168","https://openalex.org/W3125261728"],"related_works":["https://openalex.org/W4226266853","https://openalex.org/W4245701730","https://openalex.org/W4210252074","https://openalex.org/W2511794504","https://openalex.org/W3092201768","https://openalex.org/W2911648135","https://openalex.org/W2886451445","https://openalex.org/W3108449883","https://openalex.org/W2551093110","https://openalex.org/W2796632413"],"abstract_inverted_index":{"ABSTRACT":[0],"The":[1,72],"\u201cbig":[2],"data\u201d":[3],"movement":[4],"promises":[5],"to":[6,18,27,42,50,66,117,125,147],"deliver":[7],"better":[8],"decisions":[9],"in":[10,69,115,123],"all":[11],"aspects":[12],"of":[13,34,93,107,151],"our":[14],"lives":[15],"from":[16,30,40,100],"business":[17],"science":[19],"health,":[20],"and":[21,61,91,121,142],"government":[22],"by":[23],"using":[24],"computational":[25,64,95],"techniques":[26],"identify":[28,67],"patterns":[29,68],"large":[31,59,70],"historical":[32],"collections":[33],"data.":[35,101,153],"Although":[36],"a":[37,94],"unified":[38],"view":[39],"curation":[41],"analysis":[43],"has":[44],"been":[45],"proposed,":[46],"current":[47],"research":[48,134],"appears":[49],"have":[51,85],"polarized":[52],"into":[53],"two":[54],"separate":[55],"groups:":[56],"those":[57,62],"curating":[58],"datasets":[60],"developing":[63],"methods":[65],"datasets.":[71],"case":[73],"study":[74],"presented":[75],"here":[76],"demonstrates":[77],"the":[78,87,105,108,131,138,149],"enormous":[79],"impact":[80],"that":[81,97,111,135],"parameter":[82,109],"tuning":[83],"can":[84],"on":[86,137],"resulting":[88],"accuracy,":[89],"precision,":[90],"recall":[92],"model":[96],"is":[98],"generated":[99],"It":[102],"also":[103],"illustrates":[104],"vastness":[106],"space":[110],"must":[112],"be":[113],"searched":[114],"order":[116,124],"produce":[118],"optimal":[119],"models":[120],"curated":[122],"avoid":[126],"redundant":[127],"experiments.":[128],"This":[129],"highlights":[130],"need":[132],"for":[133],"focuses":[136],"gap":[139],"between":[140],"collection":[141],"analytics":[143],"if":[144],"we":[145],"are":[146],"realize":[148],"potential":[150],"big":[152]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}