{"id":"https://openalex.org/W2914584435","doi":"https://doi.org/10.1109/bigdata.2018.8622601","title":"Statistical Methods for Generating Synthetic Email Data Sets","display_name":"Statistical Methods for Generating Synthetic Email Data Sets","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914584435","doi":"https://doi.org/10.1109/bigdata.2018.8622601","mag":"2914584435"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5071126745","display_name":"Karolyn O. Babalola","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karolyn O. Babalola","raw_affiliation_strings":["IvySys Technologies, LLC, Arlington, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IvySys Technologies, LLC, Arlington, VA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020668258","display_name":"Otis B. Jennings","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Otis B. Jennings","raw_affiliation_strings":["IvySys Technologies, LLC, Arlington, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IvySys Technologies, LLC, Arlington, VA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049041400","display_name":"Urdiales Esteban","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Esteban Urdiales","raw_affiliation_strings":["IvySys Technologies, LLC, Arlington, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IvySys Technologies, LLC, Arlington, VA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009487760","display_name":"James A. DeBardelaben","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James A. DeBardelaben","raw_affiliation_strings":["IvySys Technologies, LLC, Arlington, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IvySys Technologies, LLC, Arlington, VA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3584,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83582902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"23","issue":null,"first_page":"3986","last_page":"3990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9735000133514404,"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":0.8187856078147888},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.6466802954673767},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6312605142593384},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.571434736251831},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5361535549163818},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4622132182121277},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.4582982659339905},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3899502754211426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33822333812713623},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.18118807673454285},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.09135740995407104},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09121838212013245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187856078147888},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.6466802954673767},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6312605142593384},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.571434736251831},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5361535549163818},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4622132182121277},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.4582982659339905},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3899502754211426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33822333812713623},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.18118807673454285},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.09135740995407104},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09121838212013245},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2018.8622601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4699999988079071,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W68896595","https://openalex.org/W189559790","https://openalex.org/W1603920809","https://openalex.org/W1960686302","https://openalex.org/W1978479505","https://openalex.org/W2061100700","https://openalex.org/W2067247412","https://openalex.org/W2105427683","https://openalex.org/W2282889668","https://openalex.org/W4240303379","https://openalex.org/W6602847750","https://openalex.org/W6607822645","https://openalex.org/W6636209487","https://openalex.org/W6695809446"],"related_works":["https://openalex.org/W2350702655","https://openalex.org/W2319685803","https://openalex.org/W2026012944","https://openalex.org/W2359486277","https://openalex.org/W2289334277","https://openalex.org/W2785984867","https://openalex.org/W2355334280","https://openalex.org/W3122113541","https://openalex.org/W3123376079","https://openalex.org/W2062963425"],"abstract_inverted_index":{"This":[0],"document":[1],"outlines":[2],"and":[3,21,62,82,106],"demonstrates":[4],"an":[5],"approach":[6,52],"to":[7,99],"generating":[8],"a":[9,19,47,113],"synthetic":[10,40],"email":[11,16,41,107],"dataset":[12,17],"using":[13],"the":[14,22,35,44,54,63,79,86,95,110,125,131],"Enron":[15,36,87],"as":[18],"reference":[20,88,132],"Synthetic":[23],"Transaction":[24],"Data":[25],"Generator":[26],"(STDG)":[27],"simulator":[28],"application.":[29],"With":[30,90],"statistical":[31,80],"measures":[32],"extracted":[33],"from":[34],"dataset,":[37],"we":[38,76,93],"generate":[39,101],"threads":[42],"within":[43,109],"confines":[45],"of":[46,57,65,85,103,124,130],"fictitious":[48],"corporate":[49],"structure.":[50],"Our":[51],"extrapolates":[53],"network":[55,81],"structure":[56],"who":[58],"communicates":[59],"with":[60,128],"whom":[61],"timing":[64],"these":[66,91],"communications,":[67],"but":[68],"it":[69],"ignores":[70],"semantic":[71],"content.":[72],"To":[73],"this":[74],"end,":[75],"first":[77],"harvest":[78],"temporal":[83],"features":[84,123],"dataset.":[89,133],"features,":[92],"use":[94],"agent-based":[96],"STDG":[97],"application":[98],"stochastically":[100],"corporations":[102,111],"arbitrary":[104],"sizes":[105],"transactions":[108],"over":[112],"specified":[114],"time":[115],"period.":[116],"We":[117],"evaluate":[118],"our":[119],"methodology":[120],"by":[121],"comparing":[122],"synthetically-generated":[126],"datasets":[127],"those":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}