{"id":"https://openalex.org/W1993301568","doi":"https://doi.org/10.4304/jsw.6.9.1713-1720","title":"Enriched Format Text Categorization Using A Component Similarity Approach","display_name":"Enriched Format Text Categorization Using A Component Similarity Approach","publication_year":2011,"publication_date":"2011-08-01","ids":{"openalex":"https://openalex.org/W1993301568","doi":"https://doi.org/10.4304/jsw.6.9.1713-1720","mag":"1993301568"},"language":"en","primary_location":{"id":"doi:10.4304/jsw.6.9.1713-1720","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.6.9.1713-1720","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","raw_type":"journal-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/A5074124642","display_name":"Fei Zhu","orcid":"https://orcid.org/0000-0002-2226-2859"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Zhu","raw_affiliation_strings":["Soochow University (Suzhou)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University (Suzhou)","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101465493","display_name":"Jiong Yang","orcid":"https://orcid.org/0000-0003-0328-2317"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiong Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103154389","display_name":"Zhou Yong","orcid":"https://orcid.org/0000-0003-4261-3385"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4314,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71616462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":"9","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":0.9993000030517578,"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":0.9993000030517578,"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":0.9887999892234802,"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":0.9873999953269958,"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/computer-science","display_name":"Computer science","score":0.9080725312232971},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6653950214385986},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6617587208747864},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6519043445587158},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5486952066421509},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5357176065444946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4084283709526062},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3956681191921234},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3215565085411072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9080725312232971},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6653950214385986},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6617587208747864},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6519043445587158},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5486952066421509},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5357176065444946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4084283709526062},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3956681191921234},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3215565085411072},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4304/jsw.6.9.1713-1720","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.6.9.1713-1720","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1574322266","https://openalex.org/W1971192087","https://openalex.org/W2005422315","https://openalex.org/W2006972141","https://openalex.org/W2013477326","https://openalex.org/W2025363888","https://openalex.org/W2040241219","https://openalex.org/W2041404167","https://openalex.org/W2057212758","https://openalex.org/W2069769252","https://openalex.org/W2089534322","https://openalex.org/W2101865333","https://openalex.org/W2104136657","https://openalex.org/W2110632995","https://openalex.org/W2113925571","https://openalex.org/W2114535528","https://openalex.org/W2118020653","https://openalex.org/W2125887389","https://openalex.org/W2127416213","https://openalex.org/W2128406680","https://openalex.org/W2141667007","https://openalex.org/W2164265388","https://openalex.org/W2170338490","https://openalex.org/W2538074254","https://openalex.org/W4244203596"],"related_works":["https://openalex.org/W2085633464","https://openalex.org/W151699219","https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2078570174","https://openalex.org/W2035261173","https://openalex.org/W2125109223","https://openalex.org/W2383063829"],"abstract_inverted_index":{"Text":[0,66],"categorization":[1,12,32,62,91,117],"has":[2],"been":[3],"widely":[4],"studied":[5],"for":[6],"years.":[7],"However,":[8],"conventional":[9],"plain":[10,18],"text":[11,19,40,90],"approaches":[13],"which":[14,98,129],"work":[15,180],"good":[16],"in":[17,73,128],"behave":[20],"poor":[21],"when":[22],"they":[23],"are":[24,63,68,150],"simply":[25],"applied":[26],"to":[27,37,61,153,163],"enriched":[28,38],"format":[29,39],"texts.":[30],"An":[31],"approach":[33,80],"that":[34,58,149,171],"is":[35,41,92,133],"applicable":[36],"proposed.":[42],"During":[43],"feature":[44,48,74,78],"selection,":[45],"we":[46,143],"get":[47],"structure":[49,55,59],"distribution":[50],"weight":[51],"by":[52,94,104,118],"using":[53],"extended":[54],"model":[56],"so":[57],"affections":[60],"fully":[64],"considered.":[65],"formats":[67],"also":[69],"taken":[70],"into":[71],"account":[72],"weighting.":[75],"The":[76,89,167],"combined":[77],"weighting":[79],"strengthens":[81],"important":[82,87],"parts":[83],"and":[84,106,114,158,179],"weakens":[85],"less":[86],"ones.":[88],"fulfilled":[93],"document":[95,111],"component":[96,112,140],"similarity,":[97],"first":[99],"decomposes":[100],"document,":[101,146],"gathers":[102],"features":[103],"components":[105,148],"other":[107],"user-defined":[108],"rules,":[109],"completes":[110],"tree,":[113],"then":[115,159],"achieves":[116],"it.":[119],"We":[120],"implement":[121],"a":[122],"CSBC":[123],"based":[124],"Naive":[125],"Bayes":[126],"classifier":[127,162,173],"the":[130,134,161,172],"final":[131],"result":[132],"combination":[135],"of":[136,139],"all":[137],"classifiers":[138],"tree.":[141],"Finally":[142],"parse":[144],"OpenOffice.org":[145,156,165,177],"draw":[147],"most":[151],"related":[152],"classification":[154],"from":[155],"documents,":[157],"use":[160],"categorize":[164],"documents.":[166],"experiment":[168],"results":[169],"show":[170],"can":[174],"automatically":[175],"classify":[176],"documents":[178],"quite":[181],"well.":[182]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}