{"id":"https://openalex.org/W3005969452","doi":"https://doi.org/10.1007/s10796-020-09999-y","title":"TextBenDS: a Generic Textual Data Benchmark for Distributed Systems","display_name":"TextBenDS: a Generic Textual Data Benchmark for Distributed Systems","publication_year":2020,"publication_date":"2020-03-06","ids":{"openalex":"https://openalex.org/W3005969452","doi":"https://doi.org/10.1007/s10796-020-09999-y","mag":"3005969452"},"language":"en","primary_location":{"id":"doi:10.1007/s10796-020-09999-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10796-020-09999-y","pdf_url":null,"source":{"id":"https://openalex.org/S181659395","display_name":"Information Systems Frontiers","issn_l":"1387-3326","issn":["1387-3326","1572-9419"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems Frontiers","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://pure.au.dk/portal/en/publications/561ce487-0096-4349-b61a-8fb47a0232b2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007725540","display_name":"Ciprian\u2010Octavian Truic\u0103","orcid":"https://orcid.org/0000-0001-7292-4462"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]},{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["DK","RO"],"is_corresponding":true,"raw_author_name":"Ciprian-Octavian Truic\u0103","raw_affiliation_strings":["Computer Science and Engineering Department, Faculty of Automatic Control and Computers, University Politehnica of Bucharest, Bucharest, Romania","Department of Computer Science, Aarhus University, Aarhus, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-7292-4462","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Faculty of Automatic Control and Computers, University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"Department of Computer Science, Aarhus University, Aarhus, Denmark","institution_ids":["https://openalex.org/I204337017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026015539","display_name":"Elena\u2010Simona Apostol","orcid":"https://orcid.org/0000-0001-6397-4951"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Elena-Simona Apostol","raw_affiliation_strings":["Computer Science and Engineering Department, Faculty of Automatic Control and Computers, University Politehnica of Bucharest, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Faculty of Automatic Control and Computers, University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080624394","display_name":"J\u00e9r\u00f4me Darmont","orcid":"https://orcid.org/0000-0003-1491-384X"},"institutions":[{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"J\u00e9r\u00f4me Darmont","raw_affiliation_strings":["Universit\u00e9 de Lyon, ERIC EA 3083, Lyon 2, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lyon, ERIC EA 3083, Lyon 2, France","institution_ids":["https://openalex.org/I100532134"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104360871","display_name":"Ira Assent","orcid":"https://orcid.org/0000-0002-1091-9948"},"institutions":[{"id":"https://openalex.org/I204337017","display_name":"Aarhus University","ror":"https://ror.org/01aj84f44","country_code":"DK","type":"education","lineage":["https://openalex.org/I204337017"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ira Assent","raw_affiliation_strings":["DIGIT, Department of Computer Science, Aarhus University, Aarhus, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DIGIT, Department of Computer Science, Aarhus University, Aarhus, Denmark","institution_ids":["https://openalex.org/I204337017"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007725540"],"corresponding_institution_ids":["https://openalex.org/I204337017","https://openalex.org/I61641377"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":1.4753,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82921359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"23","issue":"1","first_page":"81","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9948999881744385,"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"}},{"id":"https://openalex.org/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8007141947746277},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6996870040893555},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4249134063720703},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38975295424461365},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34365034103393555},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06497257947921753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007141947746277},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6996870040893555},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4249134063720703},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38975295424461365},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34365034103393555},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06497257947921753},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s10796-020-09999-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10796-020-09999-y","pdf_url":null,"source":{"id":"https://openalex.org/S181659395","display_name":"Information Systems Frontiers","issn_l":"1387-3326","issn":["1387-3326","1572-9419"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems Frontiers","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/561ce487-0096-4349-b61a-8fb47a0232b2","is_oa":true,"landing_page_url":"https://pure.au.dk/portal/en/publications/561ce487-0096-4349-b61a-8fb47a0232b2","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Truic\u0103, C O, Apostol, E S, Darmont, J & Assent, I 2021, 'TextBenDS : a Generic Textual Data Benchmark for Distributed Systems', Information Systems Frontiers, vol. 23, no. 1, pp. 81-100. https://doi.org/10.1007/s10796-020-09999-y","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arXiv.org:2108.05689","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.05689","pdf_url":"https://arxiv.org/pdf/2108.05689","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-02476758v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02476758","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://link.springer.com/article/10.1007/s10796-020-09999-y","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:RePEc:spr:infosf:v:23:y:2021:i:1:d:10.1007_s10796-020-09999-y","is_oa":false,"landing_page_url":"http://link.springer.com/10.1007/s10796-020-09999-y","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/561ce487-0096-4349-b61a-8fb47a0232b2","is_oa":true,"landing_page_url":"https://pure.au.dk/portal/en/publications/561ce487-0096-4349-b61a-8fb47a0232b2","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Truic\u0103, C O, Apostol, E S, Darmont, J & Assent, I 2021, 'TextBenDS : a Generic Textual Data Benchmark for Distributed Systems', Information Systems Frontiers, vol. 23, no. 1, pp. 81-100. https://doi.org/10.1007/s10796-020-09999-y","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.49000000953674316,"display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G599328546","display_name":null,"funder_award_id":"No. PN-III-P1-1.2-PCCDI-2017-0734","funder_id":"https://openalex.org/F4320323983","funder_display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii"}],"funders":[{"id":"https://openalex.org/F4320323983","display_name":"Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii","ror":"https://ror.org/01q7jq182"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W20077218","https://openalex.org/W22394099","https://openalex.org/W86271650","https://openalex.org/W756166754","https://openalex.org/W1532325895","https://openalex.org/W1544148736","https://openalex.org/W1590405911","https://openalex.org/W1755948513","https://openalex.org/W1831820753","https://openalex.org/W1860364451","https://openalex.org/W2026481075","https://openalex.org/W2027294748","https://openalex.org/W2038412523","https://openalex.org/W2040728701","https://openalex.org/W2052312648","https://openalex.org/W2054153667","https://openalex.org/W2074306108","https://openalex.org/W2090330503","https://openalex.org/W2097484305","https://openalex.org/W2105947650","https://openalex.org/W2107743791","https://openalex.org/W2109634664","https://openalex.org/W2110086534","https://openalex.org/W2119738171","https://openalex.org/W2145139979","https://openalex.org/W2147152072","https://openalex.org/W2150102617","https://openalex.org/W2150478767","https://openalex.org/W2153252192","https://openalex.org/W2155072926","https://openalex.org/W2169213601","https://openalex.org/W2173213060","https://openalex.org/W2221398285","https://openalex.org/W2307814545","https://openalex.org/W2346026989","https://openalex.org/W2471307381","https://openalex.org/W2481320103","https://openalex.org/W2530223335","https://openalex.org/W2542459869","https://openalex.org/W2552531922","https://openalex.org/W2581611733","https://openalex.org/W2586017539","https://openalex.org/W2616102449","https://openalex.org/W2616975746","https://openalex.org/W2739369482","https://openalex.org/W2742330194","https://openalex.org/W2758725343","https://openalex.org/W2791840338","https://openalex.org/W2798720361","https://openalex.org/W2808998506","https://openalex.org/W2891453035","https://openalex.org/W2916511461","https://openalex.org/W2953285261","https://openalex.org/W3031781733","https://openalex.org/W3098310942","https://openalex.org/W3104065274","https://openalex.org/W4213009331","https://openalex.org/W4231934124","https://openalex.org/W4252060112"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526"],"abstract_inverted_index":{"Extracting":[0],"top-":[1,121,209],"k":[2,122,210],"keywords":[3,79,123,211],"and":[4,16,22,41,80,104,124,147,168,197,212],"documents":[5,76,125],"using":[6,191],"weighting":[7,66,70,97,130,140,170,202,256],"schemes":[8,71,141],"are":[9,27,37,55,67,205],"popular":[10],"techniques":[11],"employed":[12],"in":[13,30,83,207],"text":[14,186],"mining":[15],"machine":[17,109],"learning":[18,110],"for":[19,77,116,164,184,199],"different":[20],"analysis":[21,102],"retrieval":[23],"tasks.":[24],"The":[25],"weights":[26],"usually":[28],"computed":[29,68],"the":[31,46,50,62,73,93,101,105,108,117,216,220,228,243],"data":[32,167,177],"preprocessing":[33],"step,":[34],"as":[35,69],"they":[36],"costly":[38],"to":[39,91,135],"update":[40],"keep":[42],"track":[43],"of":[44,61,75,95,107,119,145,219,255],"all":[45],"modifications":[47],"performed":[48],"on":[49,129,222],"dataset.":[51],"Furthermore,":[52],"calculation":[53],"errors":[54],"introduced":[56],"when":[57],"analyzing":[58],"only":[59],"subsets":[60],"dataset,":[63],"i.e.,":[64],"wrong":[65],"use":[72],"number":[74],"scoring":[78],"documents.":[81,187,213],"Therefore,":[82],"a":[84,160,175,181],"Big":[85],"Data":[86],"context,":[87],"it":[88,132],"is":[89,133],"crucial":[90],"lower":[92],"runtime":[94],"computing":[96,120,217],"schemes,":[98,203],"without":[99],"hindering":[100],"process":[103],"accuracy":[106],"algorithms.":[111],"To":[112],"address":[113],"this":[114],"requirement":[115],"task":[118],"(which":[126],"largely":[127],"relies":[128],"schemes),":[131],"customary":[134],"design":[136],"benchmarks":[137],"that":[138,204],"compare":[139],"within":[142,227],"various":[143,195],"configurations":[144],"distributedframeworks":[146],"database":[148],"management":[149],"systems.":[150],"Thus,":[151],"we":[152],"propose":[153,190],"T":[154],"ext":[155],"B":[156],"en":[157],"DS":[158],"-":[159],"generic":[161,176],"document-oriented":[162],"benchmark":[163,173],"storing":[165,185],"textual":[166],"constructing":[169,200],"schemes.":[171,257],"Our":[172,232],"offers":[174],"model":[178],"designed":[179],"with":[180,194],"multidimensional":[182],"approach":[183],"We":[188,214],"also":[189],"aggregation":[192],"queries":[193,221],"complexities":[196],"selectivities":[198],"term":[201],"utilized":[206],"extracting":[208],"evaluate":[215],"performance":[218],"several":[223],"distributed":[224],"environments":[225],"set":[226],"Apache":[229],"Hadoop":[230],"ecosystem.":[231],"experimental":[233],"results":[234],"provide":[235],"interesting":[236],"insights.":[237],"As":[238],"an":[239],"example,":[240],"MongoDB":[241],"shows":[242],"best":[244],"overall":[245],"performance,":[246],"while":[247],"Spark\u2019s":[248],"execution":[249],"time":[250],"remains":[251],"almost":[252],"constant":[253],"regardless":[254]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}