{"id":"https://openalex.org/W2150358078","doi":"https://doi.org/10.1109/bigdata.2013.6691631","title":"The BTWorld use case for big data analytics: Description, MapReduce logical workflow, and empirical evaluation","display_name":"The BTWorld use case for big data analytics: Description, MapReduce logical workflow, and empirical evaluation","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2150358078","doi":"https://doi.org/10.1109/bigdata.2013.6691631","mag":"2150358078"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2013.6691631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big 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/A5081869535","display_name":"Tim Hegeman","orcid":null},"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":false,"raw_author_name":"Tim Hegeman","raw_affiliation_strings":["Parallel and Distributed Systems Group, Delft University of Technology, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel and Distributed Systems Group, Delft University of Technology, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009413742","display_name":"Bogdan Ghi\u021b","orcid":"https://orcid.org/0000-0002-2530-8736"},"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":false,"raw_author_name":"Bogdan Ghit","raw_affiliation_strings":["Parallel and Distributed Systems Group, Delft University of Technology, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel and Distributed Systems Group, Delft University of Technology, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047526567","display_name":"Mihai Capot\u0103","orcid":"https://orcid.org/0000-0002-7323-2393"},"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":false,"raw_author_name":"Mihai Capota","raw_affiliation_strings":["Parallel and Distributed Systems Group, Delft University of Technology, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel and Distributed Systems Group, Delft University of Technology, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068967246","display_name":"Jan Hidders","orcid":"https://orcid.org/0000-0002-8865-4329"},"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":false,"raw_author_name":"Jan Hidders","raw_affiliation_strings":["Parallel and Distributed Systems Group, Delft University of Technology, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel and Distributed Systems Group, Delft University of Technology, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049227990","display_name":"Dick Epema","orcid":"https://orcid.org/0000-0002-1015-0075"},"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":false,"raw_author_name":"Dick Epema","raw_affiliation_strings":["Parallel and Distributed Systems Group, Delft University of Technology, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel and Distributed Systems Group, Delft University of Technology, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006986556","display_name":"Alexandru Iosup","orcid":"https://orcid.org/0000-0001-8030-9398"},"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":false,"raw_author_name":"Alexandru Iosup","raw_affiliation_strings":["Parallel and Distributed Systems Group, Delft University of Technology, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel and Distributed Systems Group, Delft University of Technology, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.8748,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.97990317,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2","issue":null,"first_page":"622","last_page":"630"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.8473485708236694},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7740727663040161},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7682756185531616},{"id":"https://openalex.org/keywords/bittorrent","display_name":"BitTorrent","score":0.5462689995765686},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.497639924287796},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.39584100246429443},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3426903486251831},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2858676016330719},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2165084183216095},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.08091264963150024}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8473485708236694},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7740727663040161},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7682756185531616},{"id":"https://openalex.org/C520566109","wikidata":"https://www.wikidata.org/wiki/Q133862","display_name":"BitTorrent","level":3,"score":0.5462689995765686},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.497639924287796},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.39584100246429443},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3426903486251831},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2858676016330719},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2165084183216095},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.08091264963150024}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/bigdata.2013.6691631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2013.6691631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Big Data","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:publications/e83dd5fd-54fb-4641-b0ba-29ae71f4aa99","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/e83dd5fd-54fb-4641-b0ba-29ae71f4aa99","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Hegeman, T, Ghit, B, Capota, M, Hidders, A J H, Epema, D H J & Iosup, A 2013, The BTWorld use case for big data analytics : Description, MapReduce logical workflow, and empirical evaluation. in Proceedings of the 2013 IEEE International Conference on Big Data (Santa Clara CA, USA, October 6-9, 2013). Institute of Electrical and Electronics Engineers, pp. 622-630, conference; 2013 IEEE International Conference on Big Data; 2013-10-06; 2013-10-09, 6/10/13. https://doi.org/10.1109/BigData.2013.6691631","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:769526","is_oa":false,"landing_page_url":"http://library.tue.nl/csp/dare/LinkToRepository.csp?recordnumber=769526","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.377.3111","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.377.3111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.pds.ewi.tudelft.nl/~iosup/btworld-mapreduce-workflow13ieeebigdata.pdf","raw_type":"text"},{"id":"pmh:oai:library.tue.nl:769526","is_oa":false,"landing_page_url":"http://repository.tue.nl/769526","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:tue:oai:pure.tue.nl:publications/e83dd5fd-54fb-4641-b0ba-29ae71f4aa99","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/e83dd5fd-54fb-4641-b0ba-29ae71f4aa99","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2013 IEEE International Conference on Big Data (Santa Clara CA, USA, October 6-9, 2013), 622 - 630","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W17864305","https://openalex.org/W1485708428","https://openalex.org/W1559810148","https://openalex.org/W1598064945","https://openalex.org/W1861377444","https://openalex.org/W2045271686","https://openalex.org/W2048312304","https://openalex.org/W2098935637","https://openalex.org/W2103468764","https://openalex.org/W2104993419","https://openalex.org/W2119738171","https://openalex.org/W2127164716","https://openalex.org/W2133873843","https://openalex.org/W2142031898","https://openalex.org/W2146539853","https://openalex.org/W2150358078","https://openalex.org/W2152323874","https://openalex.org/W2153820245","https://openalex.org/W2155072926","https://openalex.org/W2157355837","https://openalex.org/W2163291889","https://openalex.org/W2166245380","https://openalex.org/W2173213060","https://openalex.org/W3102490463","https://openalex.org/W6629287752","https://openalex.org/W6639193275","https://openalex.org/W6684042893","https://openalex.org/W6785961528"],"related_works":["https://openalex.org/W2081918782","https://openalex.org/W955465953","https://openalex.org/W2347387859","https://openalex.org/W2123978205","https://openalex.org/W2001742163","https://openalex.org/W2135424926","https://openalex.org/W4240078698","https://openalex.org/W1547086384","https://openalex.org/W2138883974","https://openalex.org/W2019038080"],"abstract_inverted_index":{"The":[0],"commoditization":[1],"of":[2,14,27,69,86,102,117],"big":[3,15,44,139],"data":[4,16,45,52,105,118,140,182],"analytics,":[5],"that":[6,47,75,130],"is,":[7],"the":[8,67,96,100,132,143,152,165],"deployment,":[9],"tuning,":[10],"and":[11,31,81,99,123,126,163,193,202],"future":[12],"development":[13],"processing":[17,51,141],"platforms":[18],"such":[19],"as":[20],"MapReduce,":[21],"relies":[22],"on":[23],"a":[24,39,56,62,71,84,103,109,127],"thorough":[25],"understanding":[26,66],"relevant":[28],"use":[29,40,94,134,166,171],"cases":[30],"workloads.":[32],"In":[33],"this":[34,93,158],"work":[35],"we":[36,156],"propose":[37],"BTWorld,":[38],"case":[41,95,135,167,172],"for":[42,50,83,92,137],"time-based":[43],"analytics":[46],"is":[48],"representative":[49],"collected":[53],"periodically":[54],"from":[55],"global-scale":[57],"distributed":[58],"system.":[59],"BTWorld":[60,133],"enables":[61],"data-driven":[63],"approach":[64],"to":[65,178,205],"evolution":[68],"BitTorrent,":[70],"global":[72],"file-sharing":[73],"network":[74],"has":[76,173],"over":[77],"100":[78],"million":[79],"users":[80],"accounts":[82],"third":[85],"today's":[87,138],"upstream":[88],"traffic.":[89],"We":[90,107],"describe":[91],"analyst":[97],"questions":[98],"structure":[101],"multi-terabyte":[104],"set.":[106],"design":[108],"MapReduce-based":[110],"logical":[111],"workflow,":[112],"which":[113],"includes":[114],"three":[115],"levels":[116],"dependency":[119],"-":[120,125],"inter-query,":[121],"inter-job,":[122],"intra-job":[124],"query":[128],"diversity":[129],"make":[131],"challenging":[136,174],"tools;":[142],"workflow":[144,160],"can":[145],"be":[146],"instantiated":[147],"in":[148,151],"various":[149],"ways":[150],"MapReduce":[153,170],"stack.":[154],"Last,":[155],"instantiate":[157],"complex":[159],"using":[161],"Pig-Hadoop-HDFS":[162],"evaluate":[164],"empirically.":[168],"Our":[169],"features:":[175],"small":[176],"(kilobytes)":[177],"large":[179],"(250":[180],"MB)":[181],"sizes":[183],"per":[184],"observed":[185],"item,":[186],"excellent":[187],"(10":[188,196],"<sup":[189,197],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[190,198],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">-6</sup>":[191],")":[192,200],"very":[194],"poor":[195],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[199],"selectivity,":[201],"short":[203],"(seconds)":[204],"long":[206],"(hours)":[207],"job":[208],"duration.":[209]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}