{"id":"https://openalex.org/W2809608493","doi":"https://doi.org/10.1145/3183440.3183458","title":"Big data software analytics with Apache Spark","display_name":"Big data software analytics with Apache Spark","publication_year":2018,"publication_date":"2018-05-27","ids":{"openalex":"https://openalex.org/W2809608493","doi":"https://doi.org/10.1145/3183440.3183458","mag":"2809608493"},"language":"en","primary_location":{"id":"doi:10.1145/3183440.3183458","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183440.3183458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International Conference on Software Engineering: Companion Proceeedings","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/A5043864604","display_name":"Georgios Gousios","orcid":"https://orcid.org/0000-0002-8495-7939"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Georgios Gousios","raw_affiliation_strings":["Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043864604"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"542","last_page":"543"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9993000030517578,"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":0.9993000030517578,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9934999942779541,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9930999875068665,"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/spark","display_name":"SPARK (programming language)","score":0.856545090675354},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7771192789077759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7483009099960327},{"id":"https://openalex.org/keywords/software-analytics","display_name":"Software analytics","score":0.7108392715454102},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5992128252983093},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5850610733032227},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5350070595741272},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.48358672857284546},{"id":"https://openalex.org/keywords/data-analysis","display_name":"Data analysis","score":0.44966921210289},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.446493536233902},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.42338281869888306},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.33404189348220825},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.325234591960907},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.26466450095176697},{"id":"https://openalex.org/keywords/software-construction","display_name":"Software construction","score":0.21217754483222961},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2006644606590271},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14976337552070618}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.856545090675354},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7771192789077759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483009099960327},{"id":"https://openalex.org/C171981572","wikidata":"https://www.wikidata.org/wiki/Q7554239","display_name":"Software analytics","level":5,"score":0.7108392715454102},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5992128252983093},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5850610733032227},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5350070595741272},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.48358672857284546},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.44966921210289},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.446493536233902},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.42338281869888306},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.33404189348220825},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.325234591960907},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26466450095176697},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.21217754483222961},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2006644606590271},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14976337552070618},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3183440.3183458","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183440.3183458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th International Conference on Software Engineering: Companion Proceeedings","raw_type":"proceedings-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":10,"referenced_works":["https://openalex.org/W1972386298","https://openalex.org/W1997090065","https://openalex.org/W2110366513","https://openalex.org/W2110785760","https://openalex.org/W2189465200","https://openalex.org/W2506821214","https://openalex.org/W2703757306","https://openalex.org/W2733244695","https://openalex.org/W2733373979","https://openalex.org/W2744565623"],"related_works":["https://openalex.org/W4226266853","https://openalex.org/W2543688022","https://openalex.org/W2610964225","https://openalex.org/W2413477332","https://openalex.org/W4210252074","https://openalex.org/W3033964479","https://openalex.org/W3092201768","https://openalex.org/W2051833471","https://openalex.org/W2508885301","https://openalex.org/W3123108850"],"abstract_inverted_index":{"At":[0],"the":[1,16,44,57,74,84],"beginning":[2],"of":[3,18,53],"every":[4],"research":[5],"effort,":[6],"researchers":[7,94],"in":[8],"empirical":[9],"software":[10,92],"engineering":[11,93],"have":[12],"to":[13,28],"go":[14],"through":[15],"processes":[17],"extracting":[19],"data":[20,23,69,76,100],"from":[21],"raw":[22],"sources":[24],"and":[25,40,71,96],"transforming":[26],"them":[27],"what":[29],"their":[30],"tools":[31],"expect":[32],"as":[33,64],"inputs.":[34],"This":[35],"step":[36],"is":[37],"time":[38],"consuming":[39],"error":[41],"prone,":[42],"while":[43],"produced":[45],"artifacts":[46],"(code,":[47],"intermediate":[48],"datasets)":[49],"are":[50],"usually":[51],"not":[52],"scientific":[54],"value.":[55],"In":[56],"recent":[58],"years,":[59],"Apache":[60,88],"Spark":[61,89],"has":[62,72],"emerged":[63],"a":[65],"solid":[66],"foundation":[67],"for":[68],"science":[70],"taken":[73],"big":[75],"analytics":[77],"domain":[78],"by":[79,87],"storm.":[80],"We":[81],"believe":[82],"that":[83],"primitives":[85],"exposed":[86],"can":[90],"help":[91],"create":[95],"share":[97],"reproducible,":[98],"high-performance":[99],"analysis":[101],"pipelines.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
