{"id":"https://openalex.org/W2009512022","doi":"https://doi.org/10.1145/1166160.1166197","title":"Extending the single words-based document model","display_name":"Extending the single words-based document model","publication_year":2006,"publication_date":"2006-10-10","ids":{"openalex":"https://openalex.org/W2009512022","doi":"https://doi.org/10.1145/1166160.1166197","mag":"2009512022"},"language":"en","primary_location":{"id":"doi:10.1145/1166160.1166197","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1166160.1166197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Document engineering","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/A5043230561","display_name":"Roman Tesar","orcid":null},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Roman Tesar","raw_affiliation_strings":["University of West Bohemia","#N#University of West Bohemia#N#"],"affiliations":[{"raw_affiliation_string":"University of West Bohemia","institution_ids":["https://openalex.org/I92715842"]},{"raw_affiliation_string":"#N#University of West Bohemia#N#","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082942276","display_name":"Vaclav Strnad","orcid":null},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Vaclav Strnad","raw_affiliation_strings":["University of West Bohemia","#N#University of West Bohemia#N#"],"affiliations":[{"raw_affiliation_string":"University of West Bohemia","institution_ids":["https://openalex.org/I92715842"]},{"raw_affiliation_string":"#N#University of West Bohemia#N#","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010928435","display_name":"Karel Je\u017eek","orcid":"https://orcid.org/0000-0002-4513-8885"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Karel Jezek","raw_affiliation_strings":["University of West Bohemia","#N#University of West Bohemia#N#"],"affiliations":[{"raw_affiliation_string":"University of West Bohemia","institution_ids":["https://openalex.org/I92715842"]},{"raw_affiliation_string":"#N#University of West Bohemia#N#","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047065550","display_name":"Massimo Poesio","orcid":"https://orcid.org/0000-0001-8469-2072"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Massimo Poesio","raw_affiliation_strings":["University of Essex","University of Essex **"],"affiliations":[{"raw_affiliation_string":"University of Essex","institution_ids":["https://openalex.org/I110002522"]},{"raw_affiliation_string":"University of Essex **","institution_ids":["https://openalex.org/I110002522"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043230561"],"corresponding_institution_ids":["https://openalex.org/I92715842"],"apc_list":null,"apc_paid":null,"fwci":0.4517,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.72459673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"138","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"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":0.9998000264167786,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9947999715805054,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9890000224113464,"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/bigram","display_name":"Bigram","score":0.9784950017929077},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7990128993988037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6529918313026428},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5735079050064087},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5555640459060669},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5279145240783691},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.45957374572753906},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45555150508880615},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42354047298431396},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.423380047082901},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42177602648735046},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41280269622802734},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38029295206069946},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.16994425654411316},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.1570068895816803}],"concepts":[{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.9784950017929077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990128993988037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6529918313026428},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5735079050064087},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5555640459060669},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5279145240783691},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.45957374572753906},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45555150508880615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42354047298431396},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.423380047082901},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42177602648735046},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41280269622802734},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38029295206069946},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.16994425654411316},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1570068895816803},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1166160.1166197","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1166160.1166197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W69295931","https://openalex.org/W1549887922","https://openalex.org/W1550206324","https://openalex.org/W1730404227","https://openalex.org/W1986967485","https://openalex.org/W2023612196","https://openalex.org/W2027875450","https://openalex.org/W2030646297","https://openalex.org/W2031577530","https://openalex.org/W2037074646","https://openalex.org/W2040241219","https://openalex.org/W2100958137","https://openalex.org/W2105330923","https://openalex.org/W2117423052","https://openalex.org/W2125493259","https://openalex.org/W2143894822","https://openalex.org/W2167277498","https://openalex.org/W2170654002","https://openalex.org/W2226326746","https://openalex.org/W2435251607","https://openalex.org/W3012199806","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2182912008","https://openalex.org/W4386023432","https://openalex.org/W2968744947","https://openalex.org/W4300816751","https://openalex.org/W2126538150","https://openalex.org/W2324052717","https://openalex.org/W2186892964","https://openalex.org/W1982078379","https://openalex.org/W2015069234","https://openalex.org/W2490463991"],"abstract_inverted_index":{"The":[0,142],"basic":[1],"approach":[2,132],"in":[3,40,107,146],"text":[4,60],"categorization":[5],"is":[6,29,113,133,144,150,168],"to":[7,19,50,115,135,154],"represent":[8],"documents":[9],"by":[10],"single":[11,53],"words.":[12],"However,":[13,106],"often":[14],"other":[15,124],"features":[16,47],"are":[17,48,88,104],"utilized":[18],"achieve":[20,162],"better":[21,163],"classification":[22,43,139],"results.":[23],"In":[24],"this":[25,67],"paper,":[26],"our":[27,147],"attention":[28],"focused":[30],"on":[31,57],"bigrams":[32,84,100,137,161],"and":[33,63,76,85,101,165],"2-itemsets.":[34],"We":[35],"compare":[36],"the":[37,52,71,108,123,138],"performance":[38],"improvement":[39,98],"terms":[41],"of":[42,110],"accuracy":[44,140],"when":[45,99,127],"these":[46],"used":[49],"extend":[51,155],"words-based":[54],"document":[55,156],"representation":[56,157],"two":[58],"standard":[59],"corpora:":[61],"Reuters-21578":[62],"20":[64],"Newsgroups.":[65],"For":[66],"comparison":[68],"we":[69],"use":[70,116],"multinomial":[72],"Naive":[73],"Bayes":[74],"classifier":[75],"five":[77],"different":[78],"feature":[79,119,130],"selection":[80,120,131],"approaches.":[81],"Algorithms":[82],"for":[83],"2-itemsets":[86,103,111,159],"discovery":[87],"presented":[89],"as":[90],"well.":[91],"Our":[92],"results":[93,164],"show":[94],"a":[95,128],"statistically":[96],"significant":[97],"also":[102],"incorporated.":[105],"case":[109],"it":[112,149],"important":[114],"an":[117],"appropriate":[118],"method.":[121],"On":[122],"hand,":[125],"even":[126],"simple":[129],"applied":[134],"discover":[136],"improves.":[141],"conclusion":[143],"that,":[145],"case,":[148],"not":[151],"very":[152],"effective":[153],"with":[158],"because":[160],"discovering":[166],"them":[167],"less":[169],"resource-consuming.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}