{"id":"https://openalex.org/W2046931623","doi":"https://doi.org/10.1145/2756406.2756924","title":"Towards Use And Reuse Driven Big Data Management","display_name":"Towards Use And Reuse Driven Big Data Management","publication_year":2015,"publication_date":"2015-06-12","ids":{"openalex":"https://openalex.org/W2046931623","doi":"https://doi.org/10.1145/2756406.2756924","mag":"2046931623"},"language":"en","primary_location":{"id":"doi:10.1145/2756406.2756924","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2756406.2756924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM/IEEE-CS Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10919/51621","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017449729","display_name":"Zhiwu Xie","orcid":"https://orcid.org/0000-0002-2702-3806"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhiwu Xie","raw_affiliation_strings":["Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103259528","display_name":"Yinlin Chen","orcid":"https://orcid.org/0000-0002-3986-3108"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinlin Chen","raw_affiliation_strings":["Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008263219","display_name":"Julie Speer","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julie Speer","raw_affiliation_strings":["Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014910943","display_name":"Tyler O. Walters","orcid":"https://orcid.org/0000-0003-2161-1209"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyler Walters","raw_affiliation_strings":["Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039790869","display_name":"Pablo A. Tarazaga","orcid":"https://orcid.org/0000-0002-5443-8484"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pablo A. Tarazaga","raw_affiliation_strings":["Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011213461","display_name":"Mary Kasarda","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Kasarda","raw_affiliation_strings":["Virginia Polytechnic Institute and State University, Blacksburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5017449729"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":3.3162,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.93000699,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","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/T11937","display_name":"Research Data Management Practices","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/T11986","display_name":"Scientific Computing and Data Management","score":0.9995999932289124,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9890000224113464,"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/big-data","display_name":"Big data","score":0.792759895324707},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7728267908096313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7136538028717041},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5907762050628662},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5875380039215088},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5800465941429138},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.5782555937767029},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5652968883514404},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.553858757019043},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.49205487966537476},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.46506622433662415},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41790005564689636},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.40328913927078247},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.32740700244903564},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.256630003452301},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15213516354560852},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15173357725143433}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.792759895324707},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7728267908096313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7136538028717041},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5907762050628662},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5875380039215088},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5800465941429138},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.5782555937767029},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5652968883514404},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.553858757019043},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.49205487966537476},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.46506622433662415},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41790005564689636},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40328913927078247},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.32740700244903564},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.256630003452301},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15213516354560852},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15173357725143433},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2756406.2756924","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2756406.2756924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM/IEEE-CS Joint Conference on Digital Libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/51621","is_oa":true,"landing_page_url":"http://hdl.handle.net/10919/51621","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/51621","is_oa":true,"landing_page_url":"http://hdl.handle.net/10919/51621","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2381425","https://openalex.org/W1491444315","https://openalex.org/W1728984519","https://openalex.org/W1982235632","https://openalex.org/W1983013110","https://openalex.org/W1983454294","https://openalex.org/W1988308595","https://openalex.org/W2000394199","https://openalex.org/W2001306005","https://openalex.org/W2003423696","https://openalex.org/W2014422613","https://openalex.org/W2029084939","https://openalex.org/W2034125135","https://openalex.org/W2036833195","https://openalex.org/W2049591437","https://openalex.org/W2052443795","https://openalex.org/W2063347253","https://openalex.org/W2071125093","https://openalex.org/W2080752625","https://openalex.org/W2086630396","https://openalex.org/W2088379928","https://openalex.org/W2090674043","https://openalex.org/W2091636366","https://openalex.org/W2092168251","https://openalex.org/W2095023851","https://openalex.org/W2109470399","https://openalex.org/W2129789900","https://openalex.org/W2131159644","https://openalex.org/W2131675997","https://openalex.org/W2134070069","https://openalex.org/W2148844988","https://openalex.org/W2156838832","https://openalex.org/W2157917411","https://openalex.org/W2159818719","https://openalex.org/W2162172807","https://openalex.org/W2169328907","https://openalex.org/W2171777347","https://openalex.org/W2473455588","https://openalex.org/W2885727518","https://openalex.org/W3099590560","https://openalex.org/W4232180261","https://openalex.org/W4238044281","https://openalex.org/W6891961187"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W1504819070","https://openalex.org/W2394072345","https://openalex.org/W2988102712","https://openalex.org/W4237172707","https://openalex.org/W1501592941","https://openalex.org/W2805259584","https://openalex.org/W2773594083","https://openalex.org/W3018845829"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,21,98,131,136,153,157,173],"use":[3],"and":[4,16,58,78,86,147,156,171,192],"reuse":[5],"driven":[6],"big":[7,44,61,122],"data":[8,14,17,30,62,80,193],"management":[9,31,159],"approach":[10,49],"that":[11],"fuses":[12],"the":[13,28,34,43,69,74,93,104,111,118,143],"repository":[15,139],"processing":[18,194],"capabilities":[19],"in":[20,42],"co-located,":[22],"public":[23],"cloud.":[24],"It":[25],"answers":[26],"to":[27,53,71,76,96],"urgent":[29],"needs":[32],"from":[33],"growing":[35],"number":[36],"of":[37,135],"researchers":[38,52,75],"who":[39],"don't":[40],"fit":[41],"science/small":[45],"science":[46,115,123],"dichotomy.":[47],"This":[48,90],"will":[50],"allow":[51],"more":[54,101],"easily":[55],"use,":[56],"manage,":[57],"collaborate":[59],"around":[60],"sets,":[63],"as":[64,66,150,152],"well":[65,151],"give":[67],"librarians":[68],"opportunity":[70],"work":[72],"alongside":[73],"preserve":[77],"curate":[79],"while":[81],"it":[82],"is":[83],"still":[84],"fresh":[85],"being":[87],"actively":[88],"used.":[89],"also":[91,187],"provides":[92],"technological":[94],"foundation":[95],"foster":[97],"sharing":[99,116],"culture":[100],"aligned":[102],"with":[103,142],"open":[105],"source":[106],"software":[107],"development":[108],"paradigm":[109],"than":[110],"lone-wolf,":[112],"gift-exchanging":[113],"small":[114],"or":[117],"top-down,":[119],"highly":[120],"structured":[121],"sharing.":[124],"To":[125],"materialize":[126],"this":[127,183],"vision,":[128],"we":[129,169],"provide":[130],"system":[132,140],"architecture":[133],"consisting":[134],"scalable":[137],"digital":[138],"coupled":[141],"co-located":[144],"cloud":[145,148],"storage":[146,191],"computing,":[149],"job":[154],"scheduler":[155],"deployment":[158],"system.":[160],"Motivated":[161],"by":[162],"Virginia":[163],"Tech's":[164],"Goodwin":[165],"Hall":[166],"instrumentation":[167],"project,":[168],"implemented":[170],"evaluated":[172],"prototype.":[174],"The":[175],"results":[176],"show":[177],"not":[178],"only":[179],"sufficient":[180],"capacities":[181],"for":[182],"particular":[184],"case,":[185],"but":[186],"near":[188],"perfect":[189],"linear":[190],"scalabilities":[195],"under":[196],"moderately":[197],"high":[198],"workload.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
