{"id":"https://openalex.org/W4309389067","doi":"https://doi.org/10.1007/s10664-022-10229-z","title":"Workflow analysis of data science code in public GitHub repositories","display_name":"Workflow analysis of data science code in public GitHub repositories","publication_year":2022,"publication_date":"2022-11-19","ids":{"openalex":"https://openalex.org/W4309389067","doi":"https://doi.org/10.1007/s10664-022-10229-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/36420321"},"language":"en","primary_location":{"id":"doi:10.1007/s10664-022-10229-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-022-10229-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-022-10229-z.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10664-022-10229-z.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073190153","display_name":"Dhivyabharathi Ramasamy","orcid":"https://orcid.org/0009-0002-9056-6907"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Dhivyabharathi Ramasamy","raw_affiliation_strings":["Department of Informatics, University of Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023061106","display_name":"Cristina Sarasua","orcid":"https://orcid.org/0000-0002-2076-9584"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Cristina Sarasua","raw_affiliation_strings":["Department of Informatics, University of Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082720005","display_name":"Alberto Bacchelli","orcid":"https://orcid.org/0000-0003-0193-6823"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alberto Bacchelli","raw_affiliation_strings":["Department of Informatics, University of Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073592405","display_name":"Abraham Bernstein","orcid":"https://orcid.org/0000-0002-0128-4602"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Abraham Bernstein","raw_affiliation_strings":["Department of Informatics, University of Zurich, Zurich, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073190153"],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":7.4568,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.96712076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"28","issue":"1","first_page":"7","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T11937","display_name":"Research Data Management Practices","score":0.9965999722480774,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.989300012588501,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8029677867889404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6938071250915527},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.5529944896697998},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4727640748023987},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.41840285062789917},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.28984689712524414}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8029677867889404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6938071250915527},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5529944896697998},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4727640748023987},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.41840285062789917},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28984689712524414},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10664-022-10229-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-022-10229-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-022-10229-z.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},{"id":"pmid:36420321","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36420321","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical software engineering","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9675706","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9675706","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Empir Softw Eng","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s10664-022-10229-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-022-10229-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-022-10229-z.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320323874","display_name":"Universit\u00e4t Z\u00fcrich","ror":"https://ror.org/02crff812"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4309389067.pdf","grobid_xml":"https://content.openalex.org/works/W4309389067.grobid-xml"},"referenced_works_count":76,"referenced_works":["https://openalex.org/W1487083903","https://openalex.org/W1555199703","https://openalex.org/W1970133304","https://openalex.org/W1973540172","https://openalex.org/W1973650376","https://openalex.org/W1974752004","https://openalex.org/W1979900513","https://openalex.org/W1980050552","https://openalex.org/W1987614102","https://openalex.org/W1996651333","https://openalex.org/W1998899601","https://openalex.org/W1999861206","https://openalex.org/W2001292754","https://openalex.org/W2010229520","https://openalex.org/W2032426551","https://openalex.org/W2044102377","https://openalex.org/W2046873602","https://openalex.org/W2053154970","https://openalex.org/W2058614593","https://openalex.org/W2099571428","https://openalex.org/W2102125164","https://openalex.org/W2102365548","https://openalex.org/W2109419450","https://openalex.org/W2118202495","https://openalex.org/W2120599119","https://openalex.org/W2123179704","https://openalex.org/W2140560937","https://openalex.org/W2153246402","https://openalex.org/W2182687482","https://openalex.org/W2241506117","https://openalex.org/W2293453852","https://openalex.org/W2437061623","https://openalex.org/W2506821214","https://openalex.org/W2507380695","https://openalex.org/W2529363007","https://openalex.org/W2587937998","https://openalex.org/W2610517421","https://openalex.org/W2724503592","https://openalex.org/W2771177173","https://openalex.org/W2784241156","https://openalex.org/W2787379525","https://openalex.org/W2796040126","https://openalex.org/W2900861633","https://openalex.org/W2903359694","https://openalex.org/W2907444226","https://openalex.org/W2909198760","https://openalex.org/W2913513779","https://openalex.org/W2940731426","https://openalex.org/W2941232686","https://openalex.org/W2941629559","https://openalex.org/W2941766203","https://openalex.org/W2943238809","https://openalex.org/W2950368691","https://openalex.org/W2954370766","https://openalex.org/W2962564927","https://openalex.org/W2968484890","https://openalex.org/W2971867419","https://openalex.org/W3012094108","https://openalex.org/W3032086959","https://openalex.org/W3042955694","https://openalex.org/W3043652335","https://openalex.org/W3080875002","https://openalex.org/W3089825883","https://openalex.org/W3089843629","https://openalex.org/W3090519803","https://openalex.org/W3100026183","https://openalex.org/W3125798375","https://openalex.org/W3163379266","https://openalex.org/W3193404501","https://openalex.org/W4207017378","https://openalex.org/W4213182250","https://openalex.org/W4245421756","https://openalex.org/W4286530314","https://openalex.org/W4288083705","https://openalex.org/W4288086169","https://openalex.org/W6602452458"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W1981780420","https://openalex.org/W2182707996","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W2397952901","https://openalex.org/W2029380707","https://openalex.org/W4255934811","https://openalex.org/W2465382974"],"abstract_inverted_index":{"Abstract":[0],"Despite":[1],"the":[2,22,28,57,74,96,121,136,146,155,160,167,171,175,185,197,214,217,226,237,240,244,250,256,269],"ubiquity":[3],"of":[4,33,59,73,79,106,125,138,188,216,230,239,265],"data":[5,16,34,60,80,100,107,114,140,147,189,201,227,252,257,271],"science,":[6],"we":[7,37,83,131,165],"are":[8,204],"far":[9],"from":[10],"rigorously":[11],"understanding":[12,52,72],"how":[13],"coding":[14],"in":[15,49,90,199],"science":[17,35,81,108,141,148,190,202,228,272],"is":[18,53],"performed.":[19],"Even":[20],"though":[21],"scientific":[23],"literature":[24],"has":[25],"hinted":[26],"at":[27],"iterative":[29,75,206],"and":[30,46,76,116,123,169,207,254],"explorative":[31,77],"nature":[32,78],"coding,":[36,82,191],"need":[38],"further":[39],"empirical":[40],"evidence":[41,195],"to":[42,55,98,180,220,224,248],"understand":[43],"this":[44],"practice":[45],"its":[47],"workflows":[48],"detail.":[50],"Such":[51],"critical":[54],"recognise":[56],"needs":[58],"scientists":[61,101],"and,":[62],"for":[63,150,268],"instance,":[64],"inform":[65],"tooling":[66],"support.":[67],"To":[68],"obtain":[69],"a":[70,133,200,231],"deeper":[71,182],"analysed":[84,170],"470":[85,157],"Jupyter":[86],"notebooks":[87],"publicly":[88],"available":[89],"GitHub":[91],"repositories.":[92],"We":[93,211,235],"focused":[94],"on":[95],"extent":[97],"which":[99],"transition":[102,172],"between":[103,174],"different":[104,176],"types":[105],"activities,":[109],"or":[110],"steps":[111,149,198],"(such":[112],"as":[113,118,120],"preprocessing":[115],"modelling),":[117],"well":[119],"frequency":[122],"co-occurrence":[124],"such":[126],"transitions.":[127],"For":[128],"our":[129,192],"analysis,":[130],"developed":[132],"dataset":[134,219],"with":[135],"help":[137],"five":[139],"experts,":[142,261],"who":[143],"manually":[144],"annotated":[145,218],"each":[151],"code":[152,233],"cell":[153],"within":[154],"aforementioned":[156],"notebooks.":[158],"Using":[159],"first-order":[161],"Markov":[162],"chain":[163],"model,":[164],"extracted":[166],"transitions":[168],"probabilities":[173],"steps.":[177],"In":[178],"addition":[179],"providing":[181],"insights":[183],"into":[184],"implementation":[186],"practices":[187],"results":[193],"provide":[194],"that":[196],"workflow":[203,245],"indeed":[205],"reveal":[208],"specific":[209],"patterns.":[210],"also":[212],"evaluated":[213],"use":[215],"train":[221],"machine-learning":[222],"classifiers":[223],"predict":[225],"step(s)":[229],"given":[232],"cell.":[234],"investigate":[236],"representativeness":[238],"classification":[241],"by":[242,260],"comparing":[243],"analysis":[246],"applied":[247],"(a)":[249],"predicted":[251],"set":[253,258],"(b)":[255],"labelled":[259],"finding":[262],"an":[263],"F1-score":[264],"about":[266],"71%":[267],"10-class":[270],"step":[273],"prediction":[274],"problem.":[275]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}