{"id":"https://openalex.org/W2020761110","doi":"https://doi.org/10.1109/bigdata.2014.7004303","title":"Perldoop: Efficient execution of Perl scripts on Hadoop clusters","display_name":"Perldoop: Efficient execution of Perl scripts on Hadoop clusters","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2020761110","doi":"https://doi.org/10.1109/bigdata.2014.7004303","mag":"2020761110"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (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/A5041366936","display_name":"Jos\u00e9 M. Abu\u00edn","orcid":"https://orcid.org/0000-0001-9771-818X"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose M. Abuin","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, Spain","Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS) Universidade de Santiago de Compostela, Santiago de Compostela, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]},{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS) Universidade de Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007913294","display_name":"Juan C. Pichel","orcid":"https://orcid.org/0000-0001-9505-6493"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan C. Pichel","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, Spain","Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS) Universidade de Santiago de Compostela, Santiago de Compostela, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]},{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS) Universidade de Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084306280","display_name":"Tom\u00e1s F. Pena","orcid":"https://orcid.org/0000-0002-7622-4698"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Tomas F. Pena","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, Spain","Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS) Universidade de Santiago de Compostela, Santiago de Compostela, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]},{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS) Universidade de Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063153446","display_name":"Pablo Gamallo","orcid":"https://orcid.org/0000-0002-5819-2469"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Gamallo","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, Spain","Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS) Universidade de Santiago de Compostela, Santiago de Compostela, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]},{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS) Universidade de Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035151979","display_name":"Marcos Garc\u00eda","orcid":"https://orcid.org/0000-0002-6557-0210"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marcos Garcia","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, Spain","Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS) Universidade de Santiago de Compostela, Santiago de Compostela, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS), Universidade de Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]},{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Tecnolox\u00edas da Informaci\u00f3n (CiTIUS) Universidade de Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6408,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88127681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"5","issue":null,"first_page":"766","last_page":"771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9973999857902527,"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":0.9973999857902527,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9945999979972839,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/perl","display_name":"Perl","score":0.9465714693069458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8942379951477051},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.8460700511932373},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.7292202711105347},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.6061139702796936},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.49084144830703735},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3898121416568756}],"concepts":[{"id":"https://openalex.org/C2777002779","wikidata":"https://www.wikidata.org/wiki/Q42478","display_name":"Perl","level":2,"score":0.9465714693069458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8942379951477051},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.8460700511932373},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.7292202711105347},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.6061139702796936},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.49084144830703735},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3898121416568756}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2014.7004303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W66137051","https://openalex.org/W1493349649","https://openalex.org/W1552847225","https://openalex.org/W1995166879","https://openalex.org/W2011868114","https://openalex.org/W2031634592","https://openalex.org/W2040513965","https://openalex.org/W2078957420","https://openalex.org/W2094728533","https://openalex.org/W2103296194","https://openalex.org/W2127797489","https://openalex.org/W2143017621","https://openalex.org/W2146231755","https://openalex.org/W2158710750","https://openalex.org/W2173213060","https://openalex.org/W2199681650","https://openalex.org/W2267556340","https://openalex.org/W2514632255","https://openalex.org/W4251372957","https://openalex.org/W6629578927","https://openalex.org/W6649167791","https://openalex.org/W6670294493","https://openalex.org/W6693423001","https://openalex.org/W6903559501"],"related_works":["https://openalex.org/W2331989206","https://openalex.org/W3173828731","https://openalex.org/W45658120","https://openalex.org/W2008612003","https://openalex.org/W613088223","https://openalex.org/W2045950409","https://openalex.org/W2739025131","https://openalex.org/W4205178530","https://openalex.org/W2606876474","https://openalex.org/W1974405519"],"abstract_inverted_index":{"Hadoop":[0,26,33,47,56,94,133,155,178],"is":[1,14],"one":[2],"of":[3,8,20,52,62,114,116],"the":[4,9,21,50,60,67,150,160,168],"most":[5,19],"important":[6],"implementations":[7],"MapReduce":[10],"programming":[11],"model.":[12],"It":[13],"written":[15,29,41],"in":[16,30,42,66,171],"Java":[17,86,139],"and":[18],"programs":[22],"that":[23,78,138],"run":[24],"on":[25,93],"are":[27,164],"also":[28,34],"this":[31,70,158],"language.":[32],"provides":[35],"an":[36],"utility":[37],"to":[38,129,146,166],"execute":[39,144],"applications":[40],"other":[43],"languages,":[44],"known":[45],"as":[46],"Streaming.":[48,134,156],"However,":[49],"ease":[51],"use":[53],"provided":[54],"by":[55],"Streaming":[57],"comes":[58],"at":[59],"expense":[61],"a":[63,75,177],"noticeable":[64],"degradation":[65],"performance.":[68],"In":[69,157],"work,":[71],"we":[72],"introduce":[73],"Perldoop,":[74],"new":[76,161],"tool":[77,104],"automatically":[79],"translates":[80],"Hadoop-ready":[81],"Perl":[82,126,152],"scripts":[83],"into":[84],"its":[85],"counterparts,":[87],"which":[88,112],"can":[89],"be":[90,122,130],"directly":[91],"executed":[92,131],"while":[95],"improving":[96],"their":[97],"performance":[98],"significantly.":[99],"We":[100],"have":[101],"tested":[102],"our":[103],"using":[105,142,154,176],"several":[106],"Natural":[107],"Language":[108],"Processing":[109],"(NLP)":[110],"modules,":[111],"consist":[113],"hundreds":[115],"regular":[117],"expressions,":[118],"but":[119],"Perldoop":[120,143],"could":[121],"used":[123],"with":[124,132,180],"any":[125],"code":[127],"ready":[128],"Performance":[135],"results":[136],"show":[137],"codes":[140],"generated":[141],"up":[145],"12x":[147],"faster":[148],"than":[149,173],"original":[151],"modules":[153,163],"way,":[159],"NLP":[162],"able":[165],"process":[167],"whole":[169],"Wikipedia":[170],"less":[172],"2":[174],"hours":[175],"cluster":[179],"64":[181],"nodes.":[182]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
