{"id":"https://openalex.org/W2062293942","doi":"https://doi.org/10.1145/2110497.2110507","title":"Making data analysis expertise broadly accessible through workflows","display_name":"Making data analysis expertise broadly accessible through workflows","publication_year":2011,"publication_date":"2011-11-14","ids":{"openalex":"https://openalex.org/W2062293942","doi":"https://doi.org/10.1145/2110497.2110507","mag":"2062293942"},"language":"en","primary_location":{"id":"doi:10.1145/2110497.2110507","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2110497.2110507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th workshop on Workflows in support of large-scale science","raw_type":"proceedings-article"},"type":"conference-paper","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/A5078182123","display_name":"Matheus Hauder","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matheus Hauder","raw_affiliation_strings":["University of Southern California, Marina del Rey, CA, USA","University of Southern California, Marina Del Rey , CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Marina del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2801204180"]},{"raw_affiliation_string":"University of Southern California, Marina Del Rey , CA, USA#TAB#","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040878653","display_name":"Yolanda Gil","orcid":"https://orcid.org/0000-0001-8465-8341"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yolanda Gil","raw_affiliation_strings":["University of Southern California, Marina del Rey, CA, USA","University of Southern California, Marina Del Rey , CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Marina del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2801204180"]},{"raw_affiliation_string":"University of Southern California, Marina Del Rey , CA, USA#TAB#","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070377070","display_name":"Ricky J. Sethi","orcid":"https://orcid.org/0000-0001-5254-3750"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2801204180","display_name":"Marina Del Rey Hospital","ror":"https://ror.org/05wqyfz02","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801204180"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ricky Sethi","raw_affiliation_strings":["University of Southern California, Marina del Rey, CA, USA","University of Southern California, Marina Del Rey , CA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Marina del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2801204180"]},{"raw_affiliation_string":"University of Southern California, Marina Del Rey , CA, USA#TAB#","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351175","display_name":"Yan Liu","orcid":"https://orcid.org/0000-0003-4242-4840"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Liu","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA","[University of Southern California Los, Angeles, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[University of Southern California Los, Angeles, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053172926","display_name":"Hyunjoon Jo","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyunjoon Jo","raw_affiliation_strings":["Univesrity of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univesrity of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"86"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9988999962806702,"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/T10260","display_name":"Software Engineering Research","score":0.9965000152587891,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9926000237464905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8553153872489929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8497999906539917},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6513405442237854},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.584691047668457},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4622630178928375},{"id":"https://openalex.org/keywords/business-intelligence","display_name":"Business intelligence","score":0.4532325565814972},{"id":"https://openalex.org/keywords/software-analytics","display_name":"Software analytics","score":0.45156174898147583},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.44482147693634033},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.44027653336524963},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.4195585548877716},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.33911746740341187},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3209526538848877},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.23608306050300598},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20060384273529053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18181300163269043},{"id":"https://openalex.org/keywords/component-based-software-engineering","display_name":"Component-based software engineering","score":0.15115535259246826}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8553153872489929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8497999906539917},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6513405442237854},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.584691047668457},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4622630178928375},{"id":"https://openalex.org/C2767350","wikidata":"https://www.wikidata.org/wiki/Q6662173","display_name":"Business intelligence","level":2,"score":0.4532325565814972},{"id":"https://openalex.org/C171981572","wikidata":"https://www.wikidata.org/wiki/Q7554239","display_name":"Software analytics","level":5,"score":0.45156174898147583},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.44482147693634033},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.44027653336524963},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.4195585548877716},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.33911746740341187},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3209526538848877},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.23608306050300598},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20060384273529053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18181300163269043},{"id":"https://openalex.org/C174683762","wikidata":"https://www.wikidata.org/wiki/Q609588","display_name":"Component-based software engineering","level":4,"score":0.15115535259246826},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2110497.2110507","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2110497.2110507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th workshop on Workflows in support of large-scale science","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.222.8840","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.222.8840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.isi.edu/%7Egil/papers/hauder-etal-works11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308633","display_name":"Computing Research Association","ror":"https://ror.org/00agrkd75"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W113396932","https://openalex.org/W121155884","https://openalex.org/W1480875294","https://openalex.org/W1485293642","https://openalex.org/W1507034068","https://openalex.org/W1543320899","https://openalex.org/W1548849615","https://openalex.org/W1570448133","https://openalex.org/W1880262756","https://openalex.org/W1967841763","https://openalex.org/W1980511697","https://openalex.org/W1987004884","https://openalex.org/W2081869978","https://openalex.org/W2096677212","https://openalex.org/W2096797897","https://openalex.org/W2114690085","https://openalex.org/W2115570304","https://openalex.org/W2143543488","https://openalex.org/W2154752825","https://openalex.org/W2165254944","https://openalex.org/W2183019596","https://openalex.org/W2381400491","https://openalex.org/W2435251607","https://openalex.org/W2963331646"],"related_works":["https://openalex.org/W3130756120","https://openalex.org/W2150941767","https://openalex.org/W4226266853","https://openalex.org/W4210252074","https://openalex.org/W2413477332","https://openalex.org/W3068949829","https://openalex.org/W3033964479","https://openalex.org/W3092201768","https://openalex.org/W2051833471","https://openalex.org/W3123352720"],"abstract_inverted_index":{"The":[0,59,91],"demand":[1],"for":[2,34,40],"advanced":[3],"skills":[4,134],"in":[5,53],"data":[6,31,76,102,127],"analysis":[7,103],"spans":[8],"many":[9],"areas":[10],"of":[11,101,108],"science,":[12],"computing,":[13],"and":[14,28,45,78,130],"business":[15],"analytics.":[16,36],"This":[17],"paper":[18],"discusses":[19],"how":[20,67],"non-expert":[21],"users":[22,124],"reuse":[23],"workflows":[24,39,60,107,137],"created":[25],"by":[26],"experts":[27],"representing":[29],"complex":[30],"mining":[32],"processes":[33],"text":[35,55],"They":[37],"include":[38],"document":[41,43],"classification,":[42],"clustering,":[44],"topic":[46],"detection,":[47],"all":[48],"assembled":[49],"from":[50],"components":[51,70],"available":[52],"well-known":[54],"analytics":[56],"software":[57],"libraries.":[58],"expose":[61],"to":[62,72,82,95,120,135,138],"non-experts":[63,94],"expert-level":[64],"knowledge":[65,129],"on":[66,117,122],"these":[68],"individual":[69],"need":[71],"be":[73],"combined":[74],"with":[75,98,125],"preparation":[77],"feature":[79],"selection":[80],"steps":[81],"make":[83],"the":[84],"underlying":[85],"statistical":[86],"learning":[87],"algorithms":[88],"most":[89],"effective.":[90],"framework":[92],"allows":[93],"easily":[96,113],"experiment":[97],"different":[99],"combinations":[100],"processes,":[104],"represented":[105],"as":[106],"computations":[109],"that":[110],"they":[111],"can":[112],"reconfigure.":[114],"We":[115],"report":[116],"our":[118],"experiences":[119],"date":[121],"having":[123],"limited":[126],"analytic":[128],"even":[131],"basic":[132],"programming":[133],"apply":[136],"their":[139],"data.":[140]},"counts_by_year":[{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
