{"id":"https://openalex.org/W981097920","doi":null,"title":"Text Mining Using Data Compression Models","display_name":"Text Mining Using Data Compression Models","publication_year":2012,"publication_date":"2012-11-09","ids":{"openalex":"https://openalex.org/W981097920","mag":"981097920"},"language":"en","primary_location":{"id":"pmh:oai:repozitorij.uni-lj.si:IzpisGradiva.php?id=25820","doi":null,"is_oa":true,"landing_page_url":"https://repozitorij.uni-lj.si/IzpisGradiva.php?id=25820","pdf_url":null,"source":{"id":"https://openalex.org/S4377196268","display_name":"Repository of the University of Ljubljana (University of Ljubljana)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I153976015","host_organization_name":"University of Ljubljana","host_organization_lineage":["https://openalex.org/I153976015"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ljubljana","raw_type":"info:eu-repo/semantics/doctoralThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repozitorij.uni-lj.si/IzpisGradiva.php?id=25820","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016388891","display_name":"Andrej Bratko","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Andrej Bratko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5016388891"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.483599990606308,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.483599990606308,"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/T11269","display_name":"Algorithms and Data Compression","score":0.3707999885082245,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.02669999934732914,"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/text-mining","display_name":"text mining","score":0.9639999866485596},{"id":"https://openalex.org/keywords/instance-selection","display_name":"instance selection","score":0.902999997138977},{"id":"https://openalex.org/keywords/k-means-initialization","display_name":"K-means initialization","score":0.9020000100135803},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.7979999780654907},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.9200000166893005},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"minimum description length","score":0.8709999918937683},{"id":"https://openalex.org/keywords/spam-email-detection","display_name":"email spam detection","score":0.9350000023841858},{"id":"https://openalex.org/keywords/statistical-language-models","display_name":"statistical language models","score":0.43799999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794111430644989},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6164673566818237},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.6118316650390625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5892508625984192},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5770827531814575},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.564411997795105},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5628080368041992},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5232231020927429},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5116846561431885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4577007591724396},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42478060722351074},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.4185783267021179},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.24324777722358704},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"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}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:repozitorij.uni-lj.si:IzpisGradiva.php?id=25820","doi":null,"is_oa":true,"landing_page_url":"https://repozitorij.uni-lj.si/IzpisGradiva.php?id=25820","pdf_url":null,"source":{"id":"https://openalex.org/S4377196268","display_name":"Repository of the University of Ljubljana (University of Ljubljana)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I153976015","host_organization_name":"University of Ljubljana","host_organization_lineage":["https://openalex.org/I153976015"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ljubljana","raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"pmh:oai:repozitorij.uni-lj.si:IzpisGradiva.php?id=157457","doi":null,"is_oa":true,"landing_page_url":"https://repozitorij.uni-lj.si/IzpisGradiva.php?id=157457","pdf_url":"https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=184925&dn=","source":{"id":"https://openalex.org/S4377196268","display_name":"Repository of the University of Ljubljana (University of Ljubljana)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I153976015","host_organization_name":"University of Ljubljana","host_organization_lineage":["https://openalex.org/I153976015"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"mag:981097920","doi":null,"is_oa":false,"landing_page_url":"http://eprints.fri.uni-lj.si/1925/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:repozitorij.uni-lj.si:IzpisGradiva.php?id=25820","doi":null,"is_oa":true,"landing_page_url":"https://repozitorij.uni-lj.si/IzpisGradiva.php?id=25820","pdf_url":null,"source":{"id":"https://openalex.org/S4377196268","display_name":"Repository of the University of Ljubljana (University of Ljubljana)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I153976015","host_organization_name":"University of Ljubljana","host_organization_lineage":["https://openalex.org/I153976015"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ljubljana","raw_type":"info:eu-repo/semantics/doctoralThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W981097920.pdf","grobid_xml":"https://content.openalex.org/works/W981097920.grobid-xml"},"referenced_works_count":174,"referenced_works":["https://openalex.org/W40510259","https://openalex.org/W44395966","https://openalex.org/W50505036","https://openalex.org/W66884126","https://openalex.org/W67332896","https://openalex.org/W69867230","https://openalex.org/W79904334","https://openalex.org/W87844232","https://openalex.org/W114599062","https://openalex.org/W119220656","https://openalex.org/W120415783","https://openalex.org/W170826001","https://openalex.org/W171854839","https://openalex.org/W178106347","https://openalex.org/W201187342","https://openalex.org/W202113353","https://openalex.org/W1248851061","https://openalex.org/W1484084878","https://openalex.org/W1489608363","https://openalex.org/W1490796714","https://openalex.org/W1492327544","https://openalex.org/W1494730498","https://openalex.org/W1495837896","https://openalex.org/W1506201763","https://openalex.org/W1506212051","https://openalex.org/W1509016759","https://openalex.org/W1514078281","https://openalex.org/W1514940655","https://openalex.org/W1523411787","https://openalex.org/W1528113134","https://openalex.org/W1528361845","https://openalex.org/W1534506107","https://openalex.org/W1547720490","https://openalex.org/W1574862351","https://openalex.org/W1585280831","https://openalex.org/W1588594383","https://openalex.org/W1594112393","https://openalex.org/W1598571137","https://openalex.org/W1605925311","https://openalex.org/W1638203394","https://openalex.org/W1640718925","https://openalex.org/W1651093245","https://openalex.org/W1761022139","https://openalex.org/W1779680350","https://openalex.org/W1813610639","https://openalex.org/W1924689489","https://openalex.org/W1947673060","https://openalex.org/W1973264045","https://openalex.org/W1974927094","https://openalex.org/W1978394996","https://openalex.org/W1978633512","https://openalex.org/W1987947967","https://openalex.org/W1989037929","https://openalex.org/W1990653637","https://openalex.org/W1991133427","https://openalex.org/W1995875735","https://openalex.org/W1997404989","https://openalex.org/W1997452128","https://openalex.org/W2001738676","https://openalex.org/W2002586964","https://openalex.org/W2005097301","https://openalex.org/W2005422315","https://openalex.org/W2006681603","https://openalex.org/W2011805409","https://openalex.org/W2015585187","https://openalex.org/W2026302857","https://openalex.org/W2027305455","https://openalex.org/W2033672007","https://openalex.org/W2040717637","https://openalex.org/W2040870580","https://openalex.org/W2046419776","https://openalex.org/W2049633694","https://openalex.org/W2054658115","https://openalex.org/W2055294489","https://openalex.org/W2060108852","https://openalex.org/W2061958896","https://openalex.org/W2064235697","https://openalex.org/W2068782468","https://openalex.org/W2072994259","https://openalex.org/W2073459066","https://openalex.org/W2076998631","https://openalex.org/W2080021732","https://openalex.org/W2081401338","https://openalex.org/W2081798681","https://openalex.org/W2085989833","https://openalex.org/W2088930249","https://openalex.org/W2089319476","https://openalex.org/W2090547656","https://openalex.org/W2090755665","https://openalex.org/W2092559021","https://openalex.org/W2096476632","https://openalex.org/W2097045838","https://openalex.org/W2097333193","https://openalex.org/W2097681719","https://openalex.org/W2099111195","https://openalex.org/W2100155737","https://openalex.org/W2101919228","https://openalex.org/W2102098892","https://openalex.org/W2103960658","https://openalex.org/W2105778889","https://openalex.org/W2106868411","https://openalex.org/W2107745473","https://openalex.org/W2108278098","https://openalex.org/W2108313281","https://openalex.org/W2108410426","https://openalex.org/W2111731805","https://openalex.org/W2112076978","https://openalex.org/W2115305054","https://openalex.org/W2117825194","https://openalex.org/W2122051577","https://openalex.org/W2122496402","https://openalex.org/W2122962290","https://openalex.org/W2123623606","https://openalex.org/W2123959253","https://openalex.org/W2124985265","https://openalex.org/W2125055259","https://openalex.org/W2125412267","https://openalex.org/W2125598538","https://openalex.org/W2125906555","https://openalex.org/W2127042504","https://openalex.org/W2128859735","https://openalex.org/W2129652681","https://openalex.org/W2129902114","https://openalex.org/W2130175375","https://openalex.org/W2132119275","https://openalex.org/W2132130797","https://openalex.org/W2133932086","https://openalex.org/W2134814259","https://openalex.org/W2135771747","https://openalex.org/W2135909747","https://openalex.org/W2138745909","https://openalex.org/W2139440668","https://openalex.org/W2139688842","https://openalex.org/W2140679654","https://openalex.org/W2144221002","https://openalex.org/W2146092999","https://openalex.org/W2148381206","https://openalex.org/W2149684865","https://openalex.org/W2149741699","https://openalex.org/W2150593711","https://openalex.org/W2150621701","https://openalex.org/W2151023586","https://openalex.org/W2151554142","https://openalex.org/W2156909104","https://openalex.org/W2160484851","https://openalex.org/W2161488606","https://openalex.org/W2161628678","https://openalex.org/W2163294786","https://openalex.org/W2165232124","https://openalex.org/W2165340347","https://openalex.org/W2165432485","https://openalex.org/W2166064672","https://openalex.org/W2166901988","https://openalex.org/W2167172988","https://openalex.org/W2169476932","https://openalex.org/W2170892895","https://openalex.org/W2171886309","https://openalex.org/W2172780573","https://openalex.org/W2288212323","https://openalex.org/W2295278941","https://openalex.org/W2420187884","https://openalex.org/W2426031434","https://openalex.org/W2533248932","https://openalex.org/W2591589908","https://openalex.org/W2615262959","https://openalex.org/W2914331073","https://openalex.org/W2915384914","https://openalex.org/W2916045930","https://openalex.org/W2917688635","https://openalex.org/W2949071206","https://openalex.org/W2963218781","https://openalex.org/W2963673689","https://openalex.org/W2999729612","https://openalex.org/W3102372265"],"related_works":["https://openalex.org/W7005937784","https://openalex.org/W2953097228","https://openalex.org/W7097864857","https://openalex.org/W2938816492","https://openalex.org/W2890532380","https://openalex.org/W7095200348","https://openalex.org/W7220768605","https://openalex.org/W7217862742","https://openalex.org/W4233393308","https://openalex.org/W7119390100"],"abstract_inverted_index":{"The":[0,95,119,267],"idea":[1],"of":[2,18,67,80,85,90,97,137,159,169,184,192,205,237,269,277],"using":[3,141],"data":[4,19,48,68],"compression":[5,50,69,106,142,206,238,253],"algorithms":[6,31],"for":[7,54,76,123,134,144,181,208,229,240,287],"machine":[8,55,194],"learning":[9,56,132,195,288],"has":[10],"been":[11],"reinvented":[12],"many":[13],"times.":[14],"Intuitively,":[15],"compact":[16],"representations":[17],"are":[20,88,216,281,285],"possible":[21],"only":[22],"if":[23],"statistical":[24,37],"regularities":[25],"exist":[26],"in":[27,167,196,246],"the":[28,98,110,157,160,170,190,203,225,235,278],"data.":[29,118],"Compression":[30],"identify":[32],"such":[33],"patterns":[34,46],"and":[35,127,175,211,222,250,284],"build":[36],"models":[38,143,150,207,239,254],"to":[39,44,114,189,218],"describe":[40],"them.":[41],"This":[42],"ability":[43],"learn":[45],"from":[47,109],"makes":[49],"methods":[51,228,280],"instantly":[52],"attractive":[53],"purposes.\r\n\r\nIn":[57],"this":[58,165,230,258,270],"thesis,":[59],"we":[60,146],"propose":[61,147,202],"several":[62],"novel":[63],"text":[64,138,273],"mining":[65],"applications":[66],"algorithms.":[70],"We":[71,163,201,232],"introduce":[72],"a":[73,82,91,105,129,244],"compression-based":[74,214],"method":[75,120],"instance":[77],"selection,":[78],"capable":[79],"extracting":[81],"diverse":[83],"subset":[84],"documents":[86],"that":[87,148,177,213,252],"representative":[89],"larger":[92],"document":[93],"collection.":[94],"quality":[96],"sample":[99],"is":[100,112,121,272],"measured":[101],"by":[102],"how":[103],"well":[104,256],"model,":[107],"trained":[108,149],"subset,":[111],"able":[113],"predict":[115],"held-out":[116],"reference":[117],"useful":[122],"initializing":[124],"k-means":[125],"clustering,":[126],"as":[128],"pool-based":[130],"active":[131],"strategy":[133],"supervised":[135],"training":[136],"classifiers.":[139],"When":[140],"classification,":[145],"should":[151],"be":[152],"sequentially":[153],"adapted":[154],"when":[155],"evaluating":[156],"probability":[158],"classified":[161],"document.":[162],"justify":[164],"approach":[166],"terms":[168],"minimum":[171],"description":[172],"length":[173],"principle,":[174],"show":[176,212],"adaptation":[178],"improves":[179],"performance":[180],"online":[182],"filtering":[183],"email":[185],"spam.\r\n\r\nOur":[186],"research":[187],"contributes":[188],"state-of-the-art":[191],"applied":[193],"two":[197],"significant":[198],"application":[199],"domains.":[200],"use":[204,236],"spam":[209],"filtering,":[210],"filters":[215,221],"superior":[217],"traditional":[219],"tokenization-based":[220],"competitive":[223],"with":[224,289],"best":[226],"known":[227],"task.":[231],"also":[233],"consider":[234],"lexical":[241],"stress":[242],"assignment,":[243],"problem":[245],"Slovenian":[247],"speech":[248],"synthesis,":[249],"demonstrate":[251],"perform":[255],"on":[257],"task,":[259],"while":[260],"requiring":[261],"fewer":[262],"resources":[263],"than":[264],"competing":[265],"methods.":[266],"topic":[268],"thesis":[271],"mining.":[274],"However,":[275],"most":[276],"proposed":[279],"more":[282],"general,":[283],"designed":[286],"arbitrary":[290],"discrete":[291],"sequences.":[292]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}