{"id":"https://openalex.org/W2757656223","doi":"https://doi.org/10.1109/tse.2017.2754374","title":"Data Scientists in Software Teams: State of the Art and Challenges","display_name":"Data Scientists in Software Teams: State of the Art and Challenges","publication_year":2017,"publication_date":"2017-09-19","ids":{"openalex":"https://openalex.org/W2757656223","doi":"https://doi.org/10.1109/tse.2017.2754374","mag":"2757656223"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2017.2754374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2017.2754374","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","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/A5049451101","display_name":"Miryung Kim","orcid":"https://orcid.org/0000-0003-3802-1512"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miryung Kim","raw_affiliation_strings":["University of California, Los Angeles, CA"],"raw_orcid":"https://orcid.org/0000-0003-3802-1512","affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, CA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061605447","display_name":"Thomas Zimmermann","orcid":"https://orcid.org/0000-0003-4905-1469"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Zimmermann","raw_affiliation_strings":["Microsoft Research, One Microsoft Way, Redmond, WA"],"raw_orcid":"https://orcid.org/0000-0003-4905-1469","affiliations":[{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026655012","display_name":"Robert DeLine","orcid":"https://orcid.org/0000-0001-8885-8367"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert DeLine","raw_affiliation_strings":["Microsoft Research, One Microsoft Way, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069794323","display_name":"Andrew Begel","orcid":"https://orcid.org/0000-0002-7425-4818"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Begel","raw_affiliation_strings":["Microsoft Research, One Microsoft Way, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, One Microsoft Way, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":29.3711,"has_fulltext":false,"cited_by_count":204,"citation_normalized_percentile":{"value":0.9961238,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"44","issue":"11","first_page":"1024","last_page":"1038"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"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":0.9995999932289124,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598633766174316},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6587359309196472},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6478436589241028},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5823068618774414},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44030052423477173},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.41253525018692017},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3800785541534424},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09568619728088379}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598633766174316},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6587359309196472},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6478436589241028},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5823068618774414},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44030052423477173},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.41253525018692017},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3800785541534424},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09568619728088379},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"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/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},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2017.2754374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2017.2754374","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5799999833106995,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W39972009","https://openalex.org/W628136672","https://openalex.org/W1493845881","https://openalex.org/W1494137514","https://openalex.org/W1530446948","https://openalex.org/W1983956982","https://openalex.org/W1987971958","https://openalex.org/W2044102377","https://openalex.org/W2045638068","https://openalex.org/W2055611892","https://openalex.org/W2066045860","https://openalex.org/W2079756993","https://openalex.org/W2081900960","https://openalex.org/W2096447902","https://openalex.org/W2105246013","https://openalex.org/W2116199508","https://openalex.org/W2142759419","https://openalex.org/W2145383567","https://openalex.org/W2163004671","https://openalex.org/W2167926541","https://openalex.org/W2182687482","https://openalex.org/W2241506117","https://openalex.org/W2288225317","https://openalex.org/W2500787442","https://openalex.org/W2508918698","https://openalex.org/W2999729612","https://openalex.org/W3145970008","https://openalex.org/W4245072993","https://openalex.org/W4245961435","https://openalex.org/W4298882835"],"related_works":["https://openalex.org/W2787993192","https://openalex.org/W2158269427","https://openalex.org/W4381280689","https://openalex.org/W3033859939","https://openalex.org/W2847365777","https://openalex.org/W2137479650","https://openalex.org/W2245479382","https://openalex.org/W4387803644","https://openalex.org/W4210350690","https://openalex.org/W2791222374"],"abstract_inverted_index":{"The":[0],"demand":[1],"for":[2,36,79],"analyzing":[3],"large":[4],"scale":[5],"telemetry,":[6],"machine,":[7],"and":[8,28,67,82,90,102,127],"quality":[9],"data":[10,37,50,72,88,110,118,135],"is":[11],"rapidly":[12],"increasing":[13],"in":[14,120],"software":[15,23,122],"industry.":[16],"Data":[17],"scientists":[18,51,73,119],"are":[19,30],"becoming":[20],"popular":[21],"within":[22,139],"teams,":[24],"e.g.,":[25],"Facebook,":[26],"LinkedIn":[27],"Microsoft":[29,53],"creating":[31],"a":[32,44],"new":[33],"career":[34],"path":[35],"scientists.":[38,111],"In":[39],"this":[40],"paper,":[41],"we":[42],"present":[43],"large-scale":[45],"survey":[46],"with":[47,108],"793":[48],"professional":[49],"at":[52,125],"to":[54,133],"understand":[55],"their":[56,91,140],"educational":[57],"background,":[58],"problem":[59],"topics":[60],"that":[61,99],"they":[62,100,106],"work":[63],"on,":[64],"tool":[65],"usages,":[66],"activities.":[68],"We":[69,94],"cluster":[70],"these":[71],"based":[74],"on":[75,131],"the":[76,97,103,121],"time":[77],"spent":[78],"various":[80],"activities":[81],"identify":[83],"9":[84],"distinct":[85],"clusters":[86],"of":[87],"scientists,":[89],"corresponding":[92],"characteristics.":[93],"also":[95],"discuss":[96],"challenges":[98],"face":[101],"best":[104],"practices":[105],"share":[107],"other":[109],"Our":[112],"study":[113],"finds":[114],"several":[115],"trends":[116],"about":[117],"engineering":[123],"context":[124],"Microsoft,":[126],"should":[128],"inform":[129],"managers":[130],"how":[132],"leverage":[134],"science":[136],"capability":[137],"effectively":[138],"teams.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":36},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}