{"id":"https://openalex.org/W2123817815","doi":"https://doi.org/10.1109/iscis.2009.5291818","title":"LDA-based keyword selection in text categorization","display_name":"LDA-based keyword selection in text categorization","publication_year":2009,"publication_date":"2009-09-01","ids":{"openalex":"https://openalex.org/W2123817815","doi":"https://doi.org/10.1109/iscis.2009.5291818","mag":"2123817815"},"language":"en","primary_location":{"id":"doi:10.1109/iscis.2009.5291818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscis.2009.5291818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 24th International Symposium on Computer and Information Sciences","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113863291","display_name":"\u015eerafettin Ta\u015fc\u0131","orcid":null},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Serafettin Tasci","raw_affiliation_strings":["Computer Engineering Department, Bogazici University, Istanbul, Turkey","Comput. Eng. Dept., Bogazici Univ., Istanbul, Turkey#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Bogazici University, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Comput. Eng. Dept., Bogazici Univ., Istanbul, Turkey#TAB#","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030496360","display_name":"Tunga G\u00fcng\u00f6r","orcid":"https://orcid.org/0000-0001-9448-9422"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Tunga Gungor","raw_affiliation_strings":["Computer Engineering Department, Bogazici University, Istanbul, Turkey","Comput. Eng. Dept., Bogazici Univ., Istanbul, Turkey#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Bogazici University, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Comput. Eng. Dept., Bogazici Univ., Istanbul, Turkey#TAB#","institution_ids":["https://openalex.org/I4405392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405392"],"apc_list":null,"apc_paid":null,"fwci":0.4874,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.62069944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"230","last_page":"235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9944999814033508,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9922999739646912,"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/computer-science","display_name":"Computer science","score":0.7590897083282471},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7119623422622681},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7108800411224365},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.703417181968689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6795928478240967},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6165546178817749},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5737887024879456},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5187575817108154},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5104905366897583},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.49782729148864746},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4878730773925781},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36117857694625854},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32481008768081665},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.3220498263835907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7590897083282471},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7119623422622681},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7108800411224365},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.703417181968689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6795928478240967},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6165546178817749},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5737887024879456},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5187575817108154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5104905366897583},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.49782729148864746},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4878730773925781},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36117857694625854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32481008768081665},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.3220498263835907},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscis.2009.5291818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscis.2009.5291818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 24th International Symposium on Computer and Information Sciences","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.520.1132","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.520.1132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cmpe.boun.edu.tr/~gungort/papers/LDA-based Keyword Selection in Text Categorization.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1549887922","https://openalex.org/W1557927059","https://openalex.org/W1880262756","https://openalex.org/W1978394996","https://openalex.org/W2001082470","https://openalex.org/W2005422315","https://openalex.org/W2017337590","https://openalex.org/W2062425266","https://openalex.org/W2103333826","https://openalex.org/W2105948726","https://openalex.org/W2118020653","https://openalex.org/W2119479037","https://openalex.org/W2149684865","https://openalex.org/W2158660992","https://openalex.org/W2435251607","https://openalex.org/W4237791300","https://openalex.org/W4253072035","https://openalex.org/W4285719527","https://openalex.org/W6632852417","https://openalex.org/W6682304300","https://openalex.org/W6717827561"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3005513013","https://openalex.org/W2611137333","https://openalex.org/W4291700620","https://openalex.org/W4317422773"],"abstract_inverted_index":{"Text":[0],"categorization":[1,27,37],"is":[2,32],"the":[3,23,41,44,78,92,105,114,120,127,145],"task":[4],"of":[5,18,82,96],"automatically":[6],"assigning":[7],"unlabeled":[8],"text":[9,26,36,111],"documents":[10],"to":[11,74,150],"some":[12,48],"predefined":[13],"category":[14],"labels":[15],"by":[16],"means":[17],"an":[19],"induction":[20],"algorithm.":[21],"Since":[22],"data":[24],"in":[25,35,110,133],"are":[28,47],"high-dimensional,":[29],"feature":[30,99,107],"selection":[31,100,108],"broadly":[33],"used":[34,73],"systems":[38],"for":[39,98,125],"reducing":[40],"dimensionality.":[42],"In":[43,87],"literature,":[45],"there":[46],"widely":[49],"known":[50],"metrics":[51,109,147],"such":[52],"as":[53,119],"information":[54,136],"gain":[55,137],"and":[56,76,101,122,152],"document":[57,153],"frequency":[58,154],"thresholding.":[59,155],"Recently,":[60],"a":[61],"generative":[62],"graphical":[63],"model":[64,75],"called":[65],"latent":[66],"dirichlet":[67],"allocation":[68],"(LDA)":[69],"that":[70,131],"can":[71],"be":[72],"discover":[77],"underlying":[79],"topic":[80,94],"structures":[81],"textual":[83],"data,":[84],"was":[85],"proposed.":[86],"this":[88],"paper,":[89],"we":[90,116],"use":[91,117],"hidden":[93],"analysis":[95],"LDA":[97],"compare":[102],"it":[103],"with":[104],"classical":[106],"categorization.":[112],"For":[113],"experiments,":[115],"SVM":[118],"classifier":[121],"tf\u2217idf":[123],"weighting":[124,126],"terms.":[128],"We":[129],"observed":[130],"almost":[132],"all":[134,141],"metrics,":[135],"performs":[138],"best":[139],"at":[140],"keyword":[142],"numbers":[143],"while":[144],"LDA-based":[146],"perform":[148],"similar":[149],"chi-square":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}