{"id":"https://openalex.org/W2542459869","doi":"https://doi.org/10.1145/2934664","title":"Apache Spark","display_name":"Apache Spark","publication_year":2016,"publication_date":"2016-10-28","ids":{"openalex":"https://openalex.org/W2542459869","doi":"https://doi.org/10.1145/2934664","mag":"2542459869"},"language":"en","primary_location":{"id":"doi:10.1145/2934664","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2934664","pdf_url":null,"source":{"id":"https://openalex.org/S103482838","display_name":"Communications of the ACM","issn_l":"0001-0782","issn":["0001-0782","1557-7317"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications of the ACM","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/A5005554337","display_name":"Matei Zaharia","orcid":"https://orcid.org/0000-0002-7547-7204"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matei Zaharia","raw_affiliation_strings":["Stanford University, Stanford, CA and Databricks, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA and Databricks, San Francisco, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000259060","display_name":"Reynold Xin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reynold S. Xin","raw_affiliation_strings":["Databricks, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015907748","display_name":"Patrick Wendell","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Wendell","raw_affiliation_strings":["Databricks, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103417248","display_name":"Tathagata Das","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tathagata Das","raw_affiliation_strings":["Databricks, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073379366","display_name":"Michael Armbrust","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Armbrust","raw_affiliation_strings":["Databricks, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112840756","display_name":"Ankur Dave","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankur Dave","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062292480","display_name":"Xiangrui Meng","orcid":"https://orcid.org/0000-0002-2628-9960"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangrui Meng","raw_affiliation_strings":["Databricks, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055061976","display_name":"Josh Rosen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Josh Rosen","raw_affiliation_strings":["Databricks, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Databricks, San Francisco, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082710354","display_name":"Shivaram Venkataraman","orcid":"https://orcid.org/0000-0001-9575-7935"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shivaram Venkataraman","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019638","display_name":"Michael J. Franklin","orcid":"https://orcid.org/0000-0003-3332-8574"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Franklin","raw_affiliation_strings":["University of Chicago and University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of Chicago and University of California, Berkeley","institution_ids":["https://openalex.org/I95457486","https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040035859","display_name":"Ali Ghodsi","orcid":"https://orcid.org/0000-0003-1866-246X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Ghodsi","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072427753","display_name":"Joseph E. Gonzalez","orcid":"https://orcid.org/0000-0003-2921-956X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Gonzalez","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040529929","display_name":"Scott Shenker","orcid":"https://orcid.org/0000-0002-1357-7533"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Shenker","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041920173","display_name":"Ion Stoica","orcid":"https://orcid.org/0000-0002-5373-0088"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ion Stoica","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5005554337"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":444.0186,"has_fulltext":false,"cited_by_count":2285,"citation_normalized_percentile":{"value":0.99997534,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"59","issue":"11","first_page":"56","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","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/T10101","display_name":"Cloud Computing and Resource Management","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/T12292","display_name":"Graph Theory and Algorithms","score":0.9991999864578247,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9948999881744385,"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/spark","display_name":"SPARK (programming language)","score":0.858696699142456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7956627607345581},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7222885489463806},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.6390763521194458},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.6021145582199097},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4715302586555481},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.13245579600334167},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12436491250991821},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.05630484223365784}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.858696699142456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956627607345581},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7222885489463806},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6390763521194458},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.6021145582199097},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4715302586555481},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.13245579600334167},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12436491250991821},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.05630484223365784}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2934664","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2934664","pdf_url":null,"source":{"id":"https://openalex.org/S103482838","display_name":"Communications of the ACM","issn_l":"0001-0782","issn":["0001-0782","1557-7317"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications of the ACM","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G900736768","display_name":null,"funder_award_id":"CCF-1139158","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1425731158","https://openalex.org/W1448681276","https://openalex.org/W1868798185","https://openalex.org/W1976821017","https://openalex.org/W1989017925","https://openalex.org/W2000041758","https://openalex.org/W2013455564","https://openalex.org/W2038412523","https://openalex.org/W2045271686","https://openalex.org/W2051586153","https://openalex.org/W2074935284","https://openalex.org/W2078945459","https://openalex.org/W2096544401","https://openalex.org/W2100830825","https://openalex.org/W2113640782","https://openalex.org/W2122465391","https://openalex.org/W2131975293","https://openalex.org/W2139072600","https://openalex.org/W2163764145","https://openalex.org/W2170616854","https://openalex.org/W2221106743","https://openalex.org/W2394680079","https://openalex.org/W2963288913","https://openalex.org/W6663617415","https://openalex.org/W6712120708"],"related_works":["https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W2971696010","https://openalex.org/W2797182919","https://openalex.org/W2811216466","https://openalex.org/W3004458763","https://openalex.org/W4379407598"],"abstract_inverted_index":{"This":[0],"open":[1],"source":[2],"computing":[3],"framework":[4],"unifies":[5],"streaming,":[6],"batch,":[7],"and":[8],"interactive":[9],"big":[10],"data":[11],"workloads":[12],"to":[13],"unlock":[14],"new":[15],"applications.":[16]},"counts_by_year":[{"year":2026,"cited_by_count":37},{"year":2025,"cited_by_count":203},{"year":2024,"cited_by_count":195},{"year":2023,"cited_by_count":245},{"year":2022,"cited_by_count":241},{"year":2021,"cited_by_count":358},{"year":2020,"cited_by_count":363},{"year":2019,"cited_by_count":334},{"year":2018,"cited_by_count":233},{"year":2017,"cited_by_count":75},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2016-11-04T00:00:00"}
