{"id":"https://openalex.org/W2951102128","doi":"https://doi.org/10.1145/3299869.3300107","title":"Towards Understanding Data Analysis Workflows using a Large Notebook Corpus","display_name":"Towards Understanding Data Analysis Workflows using a Large Notebook Corpus","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2951102128","doi":"https://doi.org/10.1145/3299869.3300107","mag":"2951102128"},"language":"en","primary_location":{"id":"doi:10.1145/3299869.3300107","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3299869.3300107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","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/A5112838045","display_name":"Mohammed Suhail Rehman","orcid":"https://orcid.org/0000-0002-1765-1753"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammed Suhail Rehman","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5112838045"],"corresponding_institution_ids":["https://openalex.org/I39422238","https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":3.2428,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9440859,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1841","last_page":"1843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9984999895095825,"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":0.9984999895095825,"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/T10799","display_name":"Data Visualization and Analytics","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8751859664916992},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8042234182357788},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.7240103483200073},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6354091167449951},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.6233779788017273},{"id":"https://openalex.org/keywords/hobby","display_name":"Hobby","score":0.5881288647651672},{"id":"https://openalex.org/keywords/exploratory-analysis","display_name":"Exploratory analysis","score":0.47873517870903015},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.44516512751579285},{"id":"https://openalex.org/keywords/exploratory-data-analysis","display_name":"Exploratory data analysis","score":0.4364970326423645},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41858968138694763},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2338428497314453},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.22621572017669678},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.19095227122306824},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11954939365386963}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8751859664916992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8042234182357788},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.7240103483200073},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6354091167449951},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.6233779788017273},{"id":"https://openalex.org/C2780831121","wikidata":"https://www.wikidata.org/wiki/Q47728","display_name":"Hobby","level":2,"score":0.5881288647651672},{"id":"https://openalex.org/C3018260909","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory analysis","level":2,"score":0.47873517870903015},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.44516512751579285},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.4364970326423645},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41858968138694763},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2338428497314453},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22621572017669678},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.19095227122306824},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11954939365386963},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3299869.3300107","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3299869.3300107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2106146658","https://openalex.org/W2472803348","https://openalex.org/W2597525217","https://openalex.org/W2784241156","https://openalex.org/W2794885249","https://openalex.org/W2796040126","https://openalex.org/W2898377472","https://openalex.org/W2981018396","https://openalex.org/W4285663311"],"related_works":["https://openalex.org/W4245696228","https://openalex.org/W3106582992","https://openalex.org/W2106505873","https://openalex.org/W4234525880","https://openalex.org/W1487661898","https://openalex.org/W4293708072","https://openalex.org/W2301896740","https://openalex.org/W2149507315","https://openalex.org/W2905990309","https://openalex.org/W2047528632"],"abstract_inverted_index":{"The":[0],"advent":[1],"of":[2,21,30,48,80],"big":[3],"data":[4,22,56],"analysis":[5],"as":[6,9,11,36],"a":[7,12],"profession":[8],"well":[10],"hobby":[13],"has":[14],"brought":[15],"an":[16,58],"increase":[17],"in":[18,57,61],"novel":[19],"forms":[20],"exploration":[23],"and":[24,38,54,77],"analysis,":[25],"particularly":[26],"ad-hoc":[27],"analysis.":[28],"Analysis":[29],"raw":[31],"datasets":[32],"using":[33],"frameworks":[34],"such":[35,81],"pandas":[37],"R":[39],"have":[40],"become":[41],"very":[42,72],"popular":[43],"[8].":[44],"Typically":[45],"these":[46],"types":[47],"workflows":[49],"are":[50],"geared":[51],"towards":[52],"ingesting":[53],"transforming":[55],"exploratory":[59],"fashion":[60],"order":[62],"to":[63],"derive":[64],"knowledge":[65],"while":[66],"minimizing":[67],"time-to-insight.":[68],"However,":[69],"there":[70],"exists":[71],"little":[73],"work":[74],"studying":[75],"usability":[76],"performance":[78],"concerns":[79],"unstructured":[82],"workflows.":[83]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}