{"id":"https://openalex.org/W2074306108","doi":"https://doi.org/10.1147/jrd.2013.2240732","title":"Big Data text-oriented benchmark creation for Hadoop","display_name":"Big Data text-oriented benchmark creation for Hadoop","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2074306108","doi":"https://doi.org/10.1147/jrd.2013.2240732","mag":"2074306108"},"language":"en","primary_location":{"id":"doi:10.1147/jrd.2013.2240732","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2013.2240732","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","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/A5026865205","display_name":"Anne Gattiker","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210156936","display_name":"IBM Research - Austin","ror":"https://ror.org/05gjbbg60","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210156936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Gattiker","raw_affiliation_strings":["IBM Research Division, Austin Research Laboratory, Austin, TX, USA","IBM Research Division, Austin Research Laboratory, Austin, TX#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Division, Austin Research Laboratory, Austin, TX, USA","institution_ids":["https://openalex.org/I4210156936"]},{"raw_affiliation_string":"IBM Research Division, Austin Research Laboratory, Austin, TX#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067896641","display_name":"Fadi H. Gebara","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210156936","display_name":"IBM Research - Austin","ror":"https://ror.org/05gjbbg60","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210156936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"F. H. Gebara","raw_affiliation_strings":["IBM Research Division, Austin Research Laboratory, Austin, TX, USA","IBM Research Division, Austin Research Laboratory, Austin, TX#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Division, Austin Research Laboratory, Austin, TX, USA","institution_ids":["https://openalex.org/I4210156936"]},{"raw_affiliation_string":"IBM Research Division, Austin Research Laboratory, Austin, TX#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062909392","display_name":"H. Peter Hofstee","orcid":"https://orcid.org/0000-0001-9649-7338"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210156936","display_name":"IBM Research - Austin","ror":"https://ror.org/05gjbbg60","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210156936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. P. Hofstee","raw_affiliation_strings":["IBM Research Division, Austin Research Laboratory, Austin, TX, USA","IBM Research Division, Austin Research Laboratory, Austin, TX#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Division, Austin Research Laboratory, Austin, TX, USA","institution_ids":["https://openalex.org/I4210156936"]},{"raw_affiliation_string":"IBM Research Division, Austin Research Laboratory, Austin, TX#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068567697","display_name":"Jerry Hayes","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210156936","display_name":"IBM Research - Austin","ror":"https://ror.org/05gjbbg60","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210156936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. D. Hayes","raw_affiliation_strings":["IBM Research Division, Austin Research Laboratory, Austin, TX, USA","IBM Research Division, Austin Research Laboratory, Austin, TX#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Division, Austin Research Laboratory, Austin, TX, USA","institution_ids":["https://openalex.org/I4210156936"]},{"raw_affiliation_string":"IBM Research Division, Austin Research Laboratory, Austin, TX#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029715388","display_name":"Anthony Hylick","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210156936","display_name":"IBM Research - Austin","ror":"https://ror.org/05gjbbg60","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210156936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Hylick","raw_affiliation_strings":["IBM Research Division, Austin Research Laboratory, Austin, TX, USA","IBM Research Division, Austin Research Laboratory, Austin, TX#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research Division, Austin Research Laboratory, Austin, TX, USA","institution_ids":["https://openalex.org/I4210156936"]},{"raw_affiliation_string":"IBM Research Division, Austin Research Laboratory, Austin, TX#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.7066,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.98128578,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"57","issue":"3/4","first_page":"10:1","last_page":"10:6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9980999827384949,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9939000010490417,"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":0.862533688545227},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8501038551330566},{"id":"https://openalex.org/keywords/petascale-computing","display_name":"Petascale computing","score":0.8400817513465881},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8397349119186401},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7772135138511658},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.59367436170578},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.5686958432197571},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5402936339378357},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48296231031417847},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4677954316139221},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4502496123313904},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.390716016292572},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35744792222976685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.862533688545227},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8501038551330566},{"id":"https://openalex.org/C185410017","wikidata":"https://www.wikidata.org/wiki/Q7171778","display_name":"Petascale computing","level":3,"score":0.8400817513465881},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8397349119186401},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7772135138511658},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.59367436170578},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.5686958432197571},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5402936339378357},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48296231031417847},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4677954316139221},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4502496123313904},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.390716016292572},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35744792222976685},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1147/jrd.2013.2240732","is_oa":false,"landing_page_url":"https://doi.org/10.1147/jrd.2013.2240732","pdf_url":null,"source":{"id":"https://openalex.org/S4210219925","display_name":"IBM Journal of Research and Development","issn_l":"0018-8646","issn":["0018-8646","2151-8556"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320652","host_organization_name":"IBM","host_organization_lineage":["https://openalex.org/P4310320652"],"host_organization_lineage_names":["IBM"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IBM Journal of Research and Development","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2086995883","https://openalex.org/W2150102617","https://openalex.org/W2155072926","https://openalex.org/W2243099907","https://openalex.org/W2327208758","https://openalex.org/W2549460298"],"related_works":["https://openalex.org/W2019038080","https://openalex.org/W3157828377","https://openalex.org/W4377992839","https://openalex.org/W2937168573","https://openalex.org/W2261525379","https://openalex.org/W2162769527","https://openalex.org/W2805468299","https://openalex.org/W4231652189","https://openalex.org/W2889935511","https://openalex.org/W2608358066"],"abstract_inverted_index":{"Massive-scale":[0],"Big":[1,94],"Data":[2,95],"analytics":[3],"is":[4],"representative":[5,93],"of":[6,10,16,31,42,75,161],"a":[7,14,29,82,86,116,155],"new":[8,179],"class":[9],"workloads":[11],"that":[12,33,46,91,159],"justifies":[13],"rethinking":[15],"how":[17],"computing":[18],"systems":[19,53],"should":[20],"be":[21,99,133,140,144],"optimized.":[22],"This":[23],"paper":[24],"addresses":[25],"the":[26,40,124,135,147],"need":[27],"for":[28,84,178],"set":[30],"benchmarks":[32,69],"system":[34,104],"designers":[35],"can":[36,48,98],"use":[37,49],"to":[38,50,57,67,101,139,143],"measure":[39],"quality":[41],"their":[43],"designs":[44],"and":[45,78,97,112,127,174],"customers":[47],"evaluate":[51],"competing":[52],"offerings":[54],"with":[55,106,123],"respect":[56],"commonly":[58],"performed":[59],"text-oriented":[60,89,156],"workflows":[61,96],"in":[62,73],"Hadoop\u2122.":[63],"Additions":[64],"are":[65],"needed":[66],"existing":[68],"such":[70,115],"as":[71],"HiBench":[72],"terms":[74],"both":[76],"scale":[77],"relevance.":[79],"We":[80],"describe":[81],"methodology":[83],"creating":[85],"petascale":[87],"data-size":[88],"benchmark":[90,117,136],"includes":[92],"used":[100],"test":[102],"total":[103],"performance,":[105],"demands":[107],"balanced":[108],"across":[109],"storage,":[110],"network,":[111],"computation.":[113],"Creating":[114],"requires":[118],"meeting":[119],"unique":[120],"challenges":[121],"associated":[122],"data":[125],"size":[126],"its":[128],"often":[129],"unstructured":[130],"nature.":[131],"To":[132],"useful,":[134],"also":[137],"needs":[138],"sufficiently":[141],"generic":[142],"accepted":[145],"by":[146],"community":[148],"at":[149],"large.":[150],"Here,":[151],"we":[152],"focus":[153],"on":[154],"Hadoop":[157],"workflow":[158],"consists":[160],"three":[162],"common":[163],"tasks:":[164],"categorizing":[165],"text":[166],"documents,":[167],"identifying":[168],"significant":[169,176],"documents":[170,177],"within":[171],"each":[172],"category,":[173],"analyzing":[175],"topic":[180],"creation.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}