{"id":"https://openalex.org/W1972016685","doi":"https://doi.org/10.1145/1632149.1632157","title":"Evaluating text preprocessing to improve compression on maillogs","display_name":"Evaluating text preprocessing to improve compression on maillogs","publication_year":2009,"publication_date":"2009-10-12","ids":{"openalex":"https://openalex.org/W1972016685","doi":"https://doi.org/10.1145/1632149.1632157","mag":"1972016685"},"language":"en","primary_location":{"id":"doi:10.1145/1632149.1632157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1632149.1632157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 Annual Research Conference of the South African Institute of Computer Scientists and Information Technologists","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/A5026623898","display_name":"Fred Otten","orcid":null},"institutions":[{"id":"https://openalex.org/I203238179","display_name":"Rhodes University","ror":"https://ror.org/016sewp10","country_code":"ZA","type":"education","lineage":["https://openalex.org/I203238179"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Fred Otten","raw_affiliation_strings":["Rhodes University, Grahamstown, South Africa","Rhodes University,, Grahamstown, South Africa"],"affiliations":[{"raw_affiliation_string":"Rhodes University, Grahamstown, South Africa","institution_ids":["https://openalex.org/I203238179"]},{"raw_affiliation_string":"Rhodes University,, Grahamstown, South Africa","institution_ids":["https://openalex.org/I203238179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054384302","display_name":"Barry Irwin","orcid":"https://orcid.org/0000-0002-2727-2124"},"institutions":[{"id":"https://openalex.org/I203238179","display_name":"Rhodes University","ror":"https://ror.org/016sewp10","country_code":"ZA","type":"education","lineage":["https://openalex.org/I203238179"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Barry Irwin","raw_affiliation_strings":["Rhodes University, Grahamstown, South Africa","Rhodes University,, Grahamstown, South Africa"],"affiliations":[{"raw_affiliation_string":"Rhodes University, Grahamstown, South Africa","institution_ids":["https://openalex.org/I203238179"]},{"raw_affiliation_string":"Rhodes University,, Grahamstown, South Africa","institution_ids":["https://openalex.org/I203238179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082413526","display_name":"Hannah Thinyane","orcid":"https://orcid.org/0000-0003-0491-4048"},"institutions":[{"id":"https://openalex.org/I203238179","display_name":"Rhodes University","ror":"https://ror.org/016sewp10","country_code":"ZA","type":"education","lineage":["https://openalex.org/I203238179"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Hannah Thinyane","raw_affiliation_strings":["Rhodes University, Grahamstown, South Africa","Rhodes University,, Grahamstown, South Africa"],"affiliations":[{"raw_affiliation_string":"Rhodes University, Grahamstown, South Africa","institution_ids":["https://openalex.org/I203238179"]},{"raw_affiliation_string":"Rhodes University,, Grahamstown, South Africa","institution_ids":["https://openalex.org/I203238179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026623898"],"corresponding_institution_ids":["https://openalex.org/I203238179"],"apc_list":null,"apc_paid":null,"fwci":0.8724,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78820329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"44","last_page":"53"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9868000149726868,"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/T12162","display_name":"Cellular Automata and Applications","score":0.9790999889373779,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8347057104110718},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.8203595876693726},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6949684023857117},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.6278923749923706},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6114352345466614},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.5892019271850586},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5871695876121521},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.453504353761673},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37907105684280396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34450286626815796},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07957637310028076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8347057104110718},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.8203595876693726},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6949684023857117},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.6278923749923706},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6114352345466614},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.5892019271850586},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5871695876121521},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.453504353761673},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37907105684280396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34450286626815796},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07957637310028076},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.0},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1632149.1632157","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1632149.1632157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 Annual Research Conference of the South African Institute of Computer Scientists and Information Technologists","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":11,"referenced_works":["https://openalex.org/W1523411787","https://openalex.org/W1571468614","https://openalex.org/W1777016212","https://openalex.org/W2024171325","https://openalex.org/W2060108852","https://openalex.org/W2107745473","https://openalex.org/W2122962290","https://openalex.org/W2129652681","https://openalex.org/W2135771747","https://openalex.org/W2161628678","https://openalex.org/W4205241946"],"related_works":["https://openalex.org/W2989490741","https://openalex.org/W138569904","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W3092506759","https://openalex.org/W2390914021","https://openalex.org/W2389417819","https://openalex.org/W3195278891"],"abstract_inverted_index":{"Maillogs":[0],"contain":[1],"important":[2],"information":[3,13],"about":[4],"mail":[5],"which":[6],"has":[7],"been":[8],"sent":[9],"or":[10,24],"received.":[11],"This":[12,91],"can":[14,80,100],"be":[15,42,81,101,172],"used":[16,71,82,102,175,193],"for":[17,113,117,190],"statistical":[18],"purposes,":[19],"to":[20,25,31,41,72,83,103,149,157,179,194],"help":[21,26],"prevent":[22,27],"viruses":[23],"SPAM.":[28],"In":[29],"order":[30],"satisfy":[32],"regulations":[33],"and":[34,44,67,120,132,155,174],"follow":[35],"good":[36],"security":[37],"practices,":[38],"maillogs":[39,178],"need":[40],"monitored":[43],"archived.":[45],"Since":[46],"there":[47],"is":[48,59],"a":[49,115,169,184],"large":[50],"quantity":[51,75],"of":[52,56,76,87,107,124,147,186],"data,":[53],"some":[54],"form":[55],"data":[57,142],"reduction":[58],"necessary.":[60],"Data":[61],"compression":[62,86,106,143,153,161],"programs":[63],"such":[64],"as":[65],"gzip":[66],"bzip2":[68,131],"are":[69,163],"commonly":[70],"reduce":[73],"the":[74,85,105,122,128,187,191,196],"data.":[77],"Text":[78],"preprocessing":[79,140],"aid":[84],"English":[88],"text":[89,95,139],"files.":[90],"paper":[92],"evaluates":[93],"whether":[94],"preprocessing,":[96],"particularly":[97],"word":[98,118],"replacement,":[99],"improve":[104],"maillogs.":[108,145],"It":[109,165],"presents":[110],"an":[111],"algorithm":[112],"constructing":[114],"dictionary":[116,170],"replacement":[119],"provides":[121],"results":[123,188],"experiments":[125],"conducted":[126],"using":[127],"ppmd,":[129],"gzip,":[130],"7zip":[133],"programs.":[134],"These":[135],"tests":[136],"show":[137],"that":[138,168],"improves":[141],"on":[144,176],"Improvements":[146],"up":[148,156],"56":[150],"percent":[151,159,185],"in":[152,160],"time":[154],"32":[158],"ratio":[162],"achieved.":[164],"also":[166],"shows":[167],"may":[171],"generated":[173],"other":[177],"yield":[180],"reductions":[181],"within":[182],"half":[183],"achieved":[189],"maillog":[192],"generate":[195],"dictionary.":[197]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}