{"id":"https://openalex.org/W2061418317","doi":"https://doi.org/10.1109/mipro.2014.6859744","title":"Non-standard words as features for text categorization","display_name":"Non-standard words as features for text categorization","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2061418317","doi":"https://doi.org/10.1109/mipro.2014.6859744","mag":"2061418317"},"language":"en","primary_location":{"id":"doi:10.1109/mipro.2014.6859744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mipro.2014.6859744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 37th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1408.6746","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081811688","display_name":"Slobodan Beliga","orcid":"https://orcid.org/0000-0003-1407-6156"},"institutions":[{"id":"https://openalex.org/I154347574","display_name":"University of Rijeka","ror":"https://ror.org/05r8dqr10","country_code":"HR","type":"education","lineage":["https://openalex.org/I154347574"]}],"countries":["HR"],"is_corresponding":true,"raw_author_name":"Slobodan Beliga","raw_affiliation_strings":["Department of Informatics, University of Rijeka, Rijeka, Croatia","Dept. of Inf., Univ. of Rijeka, Rijeka, Croatia"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Rijeka, Rijeka, Croatia","institution_ids":["https://openalex.org/I154347574"]},{"raw_affiliation_string":"Dept. of Inf., Univ. of Rijeka, Rijeka, Croatia","institution_ids":["https://openalex.org/I154347574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040727386","display_name":"Sanda Martin\u010di\u0107-Ip\u0161i\u0107","orcid":"https://orcid.org/0000-0002-1900-5333"},"institutions":[{"id":"https://openalex.org/I154347574","display_name":"University of Rijeka","ror":"https://ror.org/05r8dqr10","country_code":"HR","type":"education","lineage":["https://openalex.org/I154347574"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Sanda Martincic-Ipsic","raw_affiliation_strings":["Department of Informatics, University of Rijeka, Rijeka, Croatia","Dept. of Inf., Univ. of Rijeka, Rijeka, Croatia"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Rijeka, Rijeka, Croatia","institution_ids":["https://openalex.org/I154347574"]},{"raw_affiliation_string":"Dept. of Inf., Univ. of Rijeka, Rijeka, Croatia","institution_ids":["https://openalex.org/I154347574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081811688"],"corresponding_institution_ids":["https://openalex.org/I154347574"],"apc_list":null,"apc_paid":null,"fwci":0.4229,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75180675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"22","issue":null,"first_page":"1165","last_page":"1169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9937000274658203,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9937000274658203,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9894999861717224,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9854000210762024,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.8440213203430176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6871791481971741},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6813680529594421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6536059379577637},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5311452746391296},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47077271342277527},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.426529198884964},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2437264621257782}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8440213203430176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6871791481971741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6813680529594421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6536059379577637},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5311452746391296},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47077271342277527},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.426529198884964},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2437264621257782},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/mipro.2014.6859744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mipro.2014.6859744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 37th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1408.6746","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1408.6746","pdf_url":"https://arxiv.org/pdf/1408.6746","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.703.7586","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.703.7586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://langnet.uniri.hr/papers/beliga/Beliga-Mipro2014-Non-Standard-Words-as-Features-for-Automatic-Text-Categorisation.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.918.8660","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.918.8660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Slobodan_Beliga/publication/265169236_Non-Standard_Words_as_Features_for_Text_Categorization/links/542933d70cf238c6ea7d1676.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.921.1895","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.921.1895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Slobodan_Beliga/publication/265169236_Non-Standard_Words_as_Features_for_Text_Categorization/links/542933d70cf238c6ea7d1676.pdf?origin%3Dpublication_detail","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1408.6746","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1408.6746","pdf_url":"https://arxiv.org/pdf/1408.6746","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W39646898","https://openalex.org/W1515087027","https://openalex.org/W1532325895","https://openalex.org/W1592212241","https://openalex.org/W2024228866","https://openalex.org/W2025679133","https://openalex.org/W2054309323","https://openalex.org/W2129914454","https://openalex.org/W2164107060","https://openalex.org/W2172099251","https://openalex.org/W3146412190","https://openalex.org/W4213009331","https://openalex.org/W4231080135","https://openalex.org/W6685117019"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2047139419"],"abstract_inverted_index":{"This":[0,150],"paper":[1],"presents":[2],"categorization":[3,60,129,133,146,192],"of":[4,36,68,78,91,95,148,173],"Croatian":[5,24,30,190],"texts":[6,191],"using":[7,137],"Non-Standard":[8],"Words":[9,14],"(NSW)":[10],"as":[11,82,102,158,165],"features.":[12],"NonStandard":[13],"are:":[15],"numbers,":[16],"dates,":[17],"acronyms,":[18],"abbreviations,":[19],"currency,":[20],"etc.":[21],"NSWs":[22,79,92,154],"in":[23,72,84,127,160],"language":[25],"are":[26,80,100,135],"determined":[27],"according":[28],"to":[29],"NSW":[31,167],"taxonomy.":[32],"For":[33],"the":[34,46,69,73,76,85,88,105,109,138,145,153,171,174,183],"purpose":[35],"this":[37],"research,":[38],"390":[39],"text":[40,128],"documents":[41],"were":[42,125],"collected":[43],"and":[44,57,121,181],"formed":[45],"SKIPEZ":[47,70],"collection":[48],"with":[49,144],"6":[50],"classes:":[51],"official,":[52],"literary,":[53],"informative,":[54],"popular,":[55],"educational":[56],"scientific.":[58],"Text":[59],"experiment":[61],"was":[62],"conducted":[63],"on":[64],"three":[65],"different":[66],"representations":[67],"collection:":[71],"first":[74,110,139],"representation,":[75,87],"frequencies":[77],"used":[81,101,126],"features;":[83,103],"second":[86],"statistic":[89],"measures":[90],"(variance,":[93],"coefficient":[94],"variation,":[96],"standard":[97,178],"deviation,":[98],"etc.)":[99],"while":[104],"third":[106],"representation":[107],"combines":[108],"two":[111],"feature":[112,140,175],"sets.":[113],"Naive":[114],"Bayes,":[115],"CN2,":[116],"C4.5,":[117],"kNN,":[118],"Classification":[119],"Trees":[120],"Random":[122],"Forest":[123],"algorithms":[124],"experiments.":[130,193],"The":[131],"best":[132],"results":[134],"achieved":[136],"set":[141],"(NSW":[142],"frequencies)":[143],"accuracy":[147],"87%.":[149],"suggests":[151],"that":[152],"should":[155,185],"be":[156,186],"considered":[157,187],"features":[159,169],"highly":[161],"inflectional":[162],"languages,":[163],"such":[164],"Croatian.":[166],"based":[168],"reduce":[170],"dimensionality":[172],"space":[176],"without":[177],"lemmatization":[179],"procedures,":[180],"therefore":[182],"bag-of-NSWs":[184],"for":[188],"further":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}