{"id":"https://openalex.org/W3192253529","doi":"https://doi.org/10.31577/cai_2021_1_57","title":"Effect of Term Weighting on Keyword Extraction in Hierarchical Category Structure","display_name":"Effect of Term Weighting on Keyword Extraction in Hierarchical Category Structure","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3192253529","doi":"https://doi.org/10.31577/cai_2021_1_57","mag":"3192253529"},"language":"en","primary_location":{"id":"doi:10.31577/cai_2021_1_57","is_oa":true,"landing_page_url":"https://doi.org/10.31577/cai_2021_1_57","pdf_url":"http://www.cai.sk/ojs/index.php/cai/article/download/2021_1_57/1075","source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.cai.sk/ojs/index.php/cai/article/download/2021_1_57/1075","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085214519","display_name":"Boonthida Chiraratanasopha","orcid":null},"institutions":[{"id":"https://openalex.org/I96916377","display_name":"Walailak University","ror":"https://ror.org/04b69g067","country_code":"TH","type":"education","lineage":["https://openalex.org/I96916377"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Boonthida Chiraratanasopha","raw_affiliation_strings":["Institute of Informatics, Walailak University, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Walailak University, Thailand","institution_ids":["https://openalex.org/I96916377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004721453","display_name":"Salin Boonbrahm","orcid":null},"institutions":[{"id":"https://openalex.org/I96916377","display_name":"Walailak University","ror":"https://ror.org/04b69g067","country_code":"TH","type":"education","lineage":["https://openalex.org/I96916377"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Salin Boonbrahm","raw_affiliation_strings":["Institute of Informatics, Walailak University, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Walailak University, Thailand","institution_ids":["https://openalex.org/I96916377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083358892","display_name":"Thanaruk Theeramunkong","orcid":"https://orcid.org/0000-0003-0744-4213"},"institutions":[{"id":"https://openalex.org/I108108428","display_name":"Thammasat University","ror":"https://ror.org/002yp7f20","country_code":"TH","type":"education","lineage":["https://openalex.org/I108108428"]},{"id":"https://openalex.org/I4210132449","display_name":"The Royal College Of Anesthesiologists Of Thailand","ror":"https://ror.org/03e4r0p06","country_code":"TH","type":"education","lineage":["https://openalex.org/I4210132449"]},{"id":"https://openalex.org/I4387154341","display_name":"Office of the Royal Society","ror":"https://ror.org/04v9gtz82","country_code":null,"type":"government","lineage":["https://openalex.org/I4387154341"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Thanaruk Theeramunkong","raw_affiliation_strings":["Sirindhorn International Institute of Technology, Thammasat University, Thailand & Associate Fellow, The Royal Society of Thailand, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sirindhorn International Institute of Technology, Thammasat University, Thailand & Associate Fellow, The Royal Society of Thailand, Thailand","institution_ids":["https://openalex.org/I4210132449","https://openalex.org/I108108428","https://openalex.org/I4387154341"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1365,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53868693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"40","issue":"1","first_page":"57","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9944999814033508,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9599000215530396,"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/weighting","display_name":"Weighting","score":0.8366695642471313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6238816380500793},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.5261423587799072},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5123990178108215},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.50152587890625},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5009384155273438},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.4945826232433319},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4935969114303589},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4469802975654602},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.43780025839805603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4349325895309448},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39567360281944275},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35453152656555176},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.1563858687877655}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8366695642471313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6238816380500793},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.5261423587799072},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5123990178108215},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.50152587890625},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5009384155273438},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4945826232433319},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4935969114303589},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4469802975654602},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.43780025839805603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4349325895309448},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39567360281944275},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35453152656555176},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.1563858687877655},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.31577/cai_2021_1_57","is_oa":true,"landing_page_url":"https://doi.org/10.31577/cai_2021_1_57","pdf_url":"http://www.cai.sk/ojs/index.php/cai/article/download/2021_1_57/1075","source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.31577/cai_2021_1_57","is_oa":true,"landing_page_url":"https://doi.org/10.31577/cai_2021_1_57","pdf_url":"http://www.cai.sk/ojs/index.php/cai/article/download/2021_1_57/1075","source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G4605047560","display_name":null,"funder_award_id":"RTA6080013","funder_id":"https://openalex.org/F4320322614","funder_display_name":"Thailand Research Fund"},{"id":"https://openalex.org/G6570415265","display_name":null,"funder_award_id":"RTA6280015","funder_id":"https://openalex.org/F4320323439","funder_display_name":"Thammasat University"},{"id":"https://openalex.org/G8145318707","display_name":null,"funder_award_id":"RTA6280015","funder_id":"https://openalex.org/F4320322614","funder_display_name":"Thailand Research Fund"}],"funders":[{"id":"https://openalex.org/F4320322437","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61"},{"id":"https://openalex.org/F4320322614","display_name":"Thailand Research Fund","ror":"https://ror.org/03gd1bh37"},{"id":"https://openalex.org/F4320323439","display_name":"Thammasat University","ror":"https://ror.org/002yp7f20"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3192253529.pdf","grobid_xml":"https://content.openalex.org/works/W3192253529.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W170134226","https://openalex.org/W1532325895","https://openalex.org/W1548039237","https://openalex.org/W1852422273","https://openalex.org/W1978394996","https://openalex.org/W1992550299","https://openalex.org/W2007499122","https://openalex.org/W2013529449","https://openalex.org/W2016718871","https://openalex.org/W2073901485","https://openalex.org/W2094986187","https://openalex.org/W2099450943","https://openalex.org/W2103479483","https://openalex.org/W2104479188","https://openalex.org/W2120761203","https://openalex.org/W2123107811","https://openalex.org/W2136075087","https://openalex.org/W2141222516","https://openalex.org/W2143774383","https://openalex.org/W2149256261","https://openalex.org/W2150766729","https://openalex.org/W2158728425","https://openalex.org/W2293478278","https://openalex.org/W2296194829","https://openalex.org/W2406235668","https://openalex.org/W2462891382","https://openalex.org/W2491159019","https://openalex.org/W2505639008","https://openalex.org/W2789995212","https://openalex.org/W2811347535","https://openalex.org/W2916485044","https://openalex.org/W3037421893","https://openalex.org/W4241475137"],"related_works":["https://openalex.org/W2382433580","https://openalex.org/W2100326285","https://openalex.org/W2180954594","https://openalex.org/W2381926679","https://openalex.org/W2052835778","https://openalex.org/W2369751049","https://openalex.org/W4281569536","https://openalex.org/W2171473894","https://openalex.org/W2741230576","https://openalex.org/W2372355498"],"abstract_inverted_index":{"While":[0],"there":[1],"have":[2,19],"been":[3,20],"several":[4],"studies":[5],"related":[6],"to":[7,85,104,160,166],"the":[8,27,79,86,140,183,197],"effect":[9],"of":[10,29,100,114,133,142,145,155,170,200],"term":[11,24,73,134],"weighting":[12,25,74,135],"on":[13,22,71],"classification":[14],"accuracy,":[15],"relatively":[16],"few":[17],"works":[18],"conducted":[21],"how":[23,72],"affects":[26,75],"quality":[28],"keywords":[30,101],"extracted":[31],"for":[32,148],"characterizing":[33],"a":[34,37,59,66,98,106,109,117,143,203],"document":[35,40,107,110],"or":[36,102,108],"category":[38,48,55,61,81,88,120,174],"(i.e.,":[39],"collection).":[41],"Moreover,":[42],"many":[43],"tasks":[44],"require":[45],"more":[46],"complicated":[47],"structure,":[49,56,82],"such":[50],"as":[51],"hierarchical":[52,80,91,173],"and":[53,68,128,164],"network":[54],"rather":[57],"than":[58],"flat":[60,87],"structure.":[62,89],"This":[63],"paper":[64],"presents":[65],"qualitative":[67],"quantitative":[69],"study":[70],"keyword":[76,150],"extraction":[77],"in":[78,83,96,116,139,172,192],"comparison":[84],"A":[90,152],"structure":[92,175],"triggers":[93],"special":[94],"characteristic":[95],"assigning":[97],"set":[99],"tags":[103],"represent":[105],"collection,":[111],"with":[112,202],"support":[113],"statistics":[115],"hierarchy,":[118],"including":[119],"itself,":[121],"its":[122,125],"parent":[123],"category,":[124],"child":[126],"categories,":[127],"sibling":[129],"categories.":[130],"An":[131],"enhancement":[132],"is":[136,158,190],"proposed":[137],"particularly":[138],"form":[141],"series":[144],"modified":[146],"TFIDF's,":[147],"improving":[149],"extraction.":[151],"text":[153],"collection":[154],"public-hearing":[156],"opinions":[157],"used":[159],"evaluate":[161],"variant":[162],"TFs":[163],"IDFs":[165],"identify":[167],"which":[168],"types":[169],"information":[171],"are":[176],"useful.":[177],"By":[178],"experiments,":[179],"we":[180],"found":[181],"that":[182],"most":[184],"effective":[185],"IDF":[186],"family,":[187],"namely":[188],"TF-IDFr,":[189],"identity>sibling>child>parent":[191],"order.":[193],"The":[194],"TF-IDFr":[195],"outperforms":[196],"vanilla":[198],"version":[199],"TFIDF":[201],"centroid-based":[204],"classifier.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}