{"id":"https://openalex.org/W2044023534","doi":"https://doi.org/10.1145/1458082.1458361","title":"Incorporating topical support documents into a small training set in text categorization","display_name":"Incorporating topical support documents into a small training set in text categorization","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W2044023534","doi":"https://doi.org/10.1145/1458082.1458361","mag":"2044023534"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458361","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","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/A5109547664","display_name":"Kyung Soon Lee","orcid":"https://orcid.org/0000-0003-2145-3802"},"institutions":[{"id":"https://openalex.org/I80611190","display_name":"Jeonbuk National University","ror":"https://ror.org/05q92br09","country_code":"KR","type":"education","lineage":["https://openalex.org/I80611190"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kyung Soon Lee","raw_affiliation_strings":["Chonbuk National University, Jeonju, South Korea","Chonbuk National University, Jeonju, South Korea#TAB#"],"affiliations":[{"raw_affiliation_string":"Chonbuk National University, Jeonju, South Korea","institution_ids":["https://openalex.org/I80611190"]},{"raw_affiliation_string":"Chonbuk National University, Jeonju, South Korea#TAB#","institution_ids":["https://openalex.org/I80611190"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5109547664"],"corresponding_institution_ids":["https://openalex.org/I80611190"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07398685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1511","last_page":"1512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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":0.9998999834060669,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9783999919891357,"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-categorization","display_name":"Text categorization","score":0.8179528117179871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7285335063934326},{"id":"https://openalex.org/keywords/economic-shortage","display_name":"Economic shortage","score":0.727603018283844},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6912258863449097},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6670821905136108},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6416947245597839},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5985344648361206},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5211953520774841},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5153936147689819},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4337748885154724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36680811643600464},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3456208109855652},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33166155219078064}],"concepts":[{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.8179528117179871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7285335063934326},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.727603018283844},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6912258863449097},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6670821905136108},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6416947245597839},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5985344648361206},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5211953520774841},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5153936147689819},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4337748885154724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36680811643600464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3456208109855652},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33166155219078064},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1458082.1458361","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1979495886","https://openalex.org/W2022298437","https://openalex.org/W2149684865","https://openalex.org/W2150102617","https://openalex.org/W2153582629","https://openalex.org/W2159737176","https://openalex.org/W2162993204"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2035261173","https://openalex.org/W2106892947","https://openalex.org/W2237299843"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,66,71,86],"incorporation":[4],"of":[5,16,21,95,113],"topical":[6,30,55,72,100,137],"support":[7,29,56,82,101,138],"documents":[8,43,47,57,126,139],"into":[9],"a":[10,14,19,35,50,92,142],"training":[11,23,97],"set":[12],"as":[13],"means":[15],"compensating":[17],"for":[18,108],"shortage":[20],"positive":[22,46,96,125],"data":[24],"in":[25,116,127],"text":[26],"categorization.":[27],"To":[28],"representation,":[31],"our":[32],"method":[33],"applies":[34],"simple":[36],"transformation":[37],"to":[38,64,141],"documents,":[39],"i.e.,":[40],"making":[41],"new":[42],"from":[44],"existing":[45],"by":[48,74],"squaring":[49],"conventional":[51],"term":[52],"weight.":[53],"The":[54],"thus":[58],"created":[59],"not":[60],"only":[61],"are":[62],"expected":[63],"preserve":[65],"topic,":[67],"but":[68],"even":[69],"improve":[70],"representation":[73,102],"emphasizing":[75],"terms":[76],"with":[77,81,91,119],"higher":[78],"weights.":[79],"Experiments":[80],"vector":[83],"machines":[84],"showed":[85],"effectiveness":[87],"on":[88,133],"RCV1":[89,114],"collection":[90],"small":[93],"number":[94],"data.":[98],"Our":[99],"achieved":[103],"52.01%":[104],"and":[105,110,123,144],"8.83%":[106],"improvements":[107],"33":[109],"56":[111],"categories":[112],"Topic":[115],"micro-averaged":[117],"F1":[118],"less":[120],"than":[121],"100":[122],"300":[124],"learning,":[128],"respectively.":[129],"Result":[130],"analyses":[131],"based":[132],"robustness":[134],"indicate":[135],"that":[136],"contribute":[140],"steady":[143],"stable":[145],"improvement.":[146]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}