{"id":"https://openalex.org/W2076033039","doi":"https://doi.org/10.1145/2616498.2616525","title":"Applying Lessons from e-Discovery to Process Big Data using HPC","display_name":"Applying Lessons from e-Discovery to Process Big Data using HPC","publication_year":2014,"publication_date":"2014-07-11","ids":{"openalex":"https://openalex.org/W2076033039","doi":"https://doi.org/10.1145/2616498.2616525","mag":"2076033039"},"language":"en","primary_location":{"id":"doi:10.1145/2616498.2616525","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2616498.2616525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Annual Conference on Extreme Science and Engineering Discovery Environment","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/A5035356929","display_name":"Sukrit Sondhi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133922","display_name":"Fulcrum Corporation (United States)","ror":"https://ror.org/03jst3522","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133922"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sukrit Sondhi","raw_affiliation_strings":["Fulcrum Worldwide, Jersey City, New Jersey, 07310"],"affiliations":[{"raw_affiliation_string":"Fulcrum Worldwide, Jersey City, New Jersey, 07310","institution_ids":["https://openalex.org/I4210133922"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109157084","display_name":"Ritu Arora","orcid":null},"institutions":[{"id":"https://openalex.org/I4388891828","display_name":"Texas Advanced Computing Center","ror":"https://ror.org/00xg4bh43","country_code":null,"type":"facility","lineage":["https://openalex.org/I4388891828","https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ritu Arora","raw_affiliation_strings":["Texas Advanced Computing Center, Austin, Texas 78758"],"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, Austin, Texas 78758","institution_ids":["https://openalex.org/I4388891828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035356929"],"corresponding_institution_ids":["https://openalex.org/I4210133922"],"apc_list":null,"apc_paid":null,"fwci":1.6275,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.89579493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9769999980926514,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9769999980926514,"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/T11719","display_name":"Data Quality and Management","score":0.9448999762535095,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9399999976158142,"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/big-data","display_name":"Big data","score":0.8140960931777954},{"id":"https://openalex.org/keywords/data-discovery","display_name":"Data discovery","score":0.7286332845687866},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.7229936718940735},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6439236402511597},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5124895572662354},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4847809672355652},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4840349555015564},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.4629083573818207},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4486826956272125},{"id":"https://openalex.org/keywords/business-process-discovery","display_name":"Business process discovery","score":0.44842249155044556},{"id":"https://openalex.org/keywords/business-process","display_name":"Business process","score":0.36802545189857483},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.2920458912849426},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.18732541799545288},{"id":"https://openalex.org/keywords/work-in-process","display_name":"Work in process","score":0.17798379063606262},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15116846561431885},{"id":"https://openalex.org/keywords/business-process-modeling","display_name":"Business process modeling","score":0.10199746489524841}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8140960931777954},{"id":"https://openalex.org/C2777516300","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data discovery","level":3,"score":0.7286332845687866},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.7229936718940735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6439236402511597},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5124895572662354},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4847809672355652},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4840349555015564},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4629083573818207},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4486826956272125},{"id":"https://openalex.org/C93453677","wikidata":"https://www.wikidata.org/wiki/Q1017580","display_name":"Business process discovery","level":5,"score":0.44842249155044556},{"id":"https://openalex.org/C85345410","wikidata":"https://www.wikidata.org/wiki/Q851587","display_name":"Business process","level":3,"score":0.36802545189857483},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.2920458912849426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.18732541799545288},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.17798379063606262},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15116846561431885},{"id":"https://openalex.org/C207505557","wikidata":"https://www.wikidata.org/wiki/Q4374012","display_name":"Business process modeling","level":4,"score":0.10199746489524841},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2616498.2616525","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2616498.2616525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Annual Conference on Extreme Science and Engineering Discovery Environment","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2150478723","https://openalex.org/W4365511202","https://openalex.org/W4300560926","https://openalex.org/W3087909741","https://openalex.org/W2345053703","https://openalex.org/W1989373239","https://openalex.org/W3184122949","https://openalex.org/W2050159024","https://openalex.org/W3194914602","https://openalex.org/W57948323"],"abstract_inverted_index":{"The":[0,97],"term":[1],"'Big":[2],"Data'":[3],"defines":[4],"large":[5,103],"datasets":[6,104],"that":[7,52,147,169],"are":[8,45,89,105,170],"difficult":[9],"to":[10,49,56,69,107,133,151],"use":[11],"and":[12,41,80,85,114,131,135,167,179],"manage":[13],"through":[14],"conventional":[15],"software":[16],"tools.":[17],"Legal":[18],"Electronic":[19],"Discovery":[20],"(e-Discovery)":[21],"is":[22],"a":[23,173],"business":[24,168],"domain":[25,146],"which":[26],"has":[27],"massive":[28],"consumption":[29],"of":[30,116,164,175],"Big":[31,119,153,176],"Data,":[32],"where":[33],"electronic":[34,81],"records":[35],"such":[36,74],"as":[37,75],"e-mail,":[38],"documents,":[39],"databases":[40],"social":[42],"media":[43],"postings":[44],"processed":[46],"in":[47,66,125],"order":[48],"discover":[50],"evidence":[51],"may":[53],"be":[54,149],"pertinent":[55],"legal/compliance":[57],"needs,":[58],"litigation":[59],"or":[60],"other":[61,126],"investigations.":[62],"Numerous":[63],"vendors":[64],"exist":[65],"the":[67,102,108,117,143,161],"market":[68],"provide":[70],"organizations":[71],"with":[72,100,172],"services":[73],"data":[76,91],"collection,":[77],"digital":[78],"forensics":[79],"discovery.":[82],"High-end":[83],"instrumentation":[84],"modern":[86],"information":[87],"technologies":[88],"creating":[90],"at":[92],"an":[93],"ever":[94],"increasing":[95],"rate.":[96],"challenges":[98,178],"associated":[99],"managing":[101],"related":[106],"capture,":[109],"storage,":[110],"search,":[111],"sharing,":[112],"analytics,":[113],"visualization":[115],"data.":[118],"Data":[120,154,177],"also":[121],"offers":[122],"unprecedented":[123],"opportunities":[124],"fields,":[127],"ranging":[128],"from":[129,142],"astronomy":[130],"biology":[132],"marketing":[134],"e-commerce.":[136],"This":[137],"paper":[138],"presents":[139],"lessons":[140],"learnt":[141],"legal":[144],"e-Discovery":[145],"can":[148],"adapted":[150],"process":[152],"effectively":[155],"on":[156],"HPC":[157],"resources,":[158],"thereby":[159],"benefitting":[160],"various":[162],"disciplines":[163],"science,":[165],"engineering":[166],"grappling":[171],"deluge":[174],"opportunities.":[180]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}