{"id":"https://openalex.org/W2945224113","doi":"https://doi.org/10.1145/3319921.3319924","title":"An Improved TF-IDF Algorithm Based on Class Discriminative Strength for Text Categorization on Desensitized Data","display_name":"An Improved TF-IDF Algorithm Based on Class Discriminative Strength for Text Categorization on Desensitized Data","publication_year":2019,"publication_date":"2019-03-15","ids":{"openalex":"https://openalex.org/W2945224113","doi":"https://doi.org/10.1145/3319921.3319924","mag":"2945224113"},"language":"en","primary_location":{"id":"doi:10.1145/3319921.3319924","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3319921.3319924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Innovation in Artificial Intelligence","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/A5100458272","display_name":"Ting Zhang","orcid":"https://orcid.org/0000-0001-6385-6963"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ting Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008501506","display_name":"Shuzhi Sam Ge","orcid":"https://orcid.org/0000-0001-5549-312X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Shuzhi Sam Ge","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China, National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596","https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100458272"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":2.3803,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.91289176,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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/T11550","display_name":"Text and Document Classification Technologies","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/T12016","display_name":"Web Data Mining and Analysis","score":0.996999979019165,"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"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9940999746322632,"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":0.7489462494850159},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.6996930837631226},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6836767196655273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5630619525909424},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5351055264472961},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5041624307632446},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.4978339672088623},{"id":"https://openalex.org/keywords/recall-rate","display_name":"Recall rate","score":0.4905375838279724},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.487784206867218},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4509541094303131},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4434043765068054},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.43922463059425354},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.426909476518631},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38338178396224976},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37058770656585693},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3502410352230072},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3452106714248657},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.14850521087646484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7489462494850159},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.6996930837631226},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6836767196655273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5630619525909424},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5351055264472961},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5041624307632446},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.4978339672088623},{"id":"https://openalex.org/C2987098735","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"Recall rate","level":2,"score":0.4905375838279724},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.487784206867218},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4509541094303131},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4434043765068054},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.43922463059425354},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.426909476518631},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38338178396224976},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37058770656585693},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3502410352230072},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3452106714248657},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.14850521087646484},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3319921.3319924","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3319921.3319924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Innovation in Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.75,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1702656447","https://openalex.org/W2011242591","https://openalex.org/W2062079906","https://openalex.org/W2141110637","https://openalex.org/W2165612380","https://openalex.org/W2349460115","https://openalex.org/W2352853785","https://openalex.org/W2369182129","https://openalex.org/W2783809651","https://openalex.org/W2784184907","https://openalex.org/W4238252015","https://openalex.org/W4252220307"],"related_works":["https://openalex.org/W2372663604","https://openalex.org/W2349460115","https://openalex.org/W1541869740","https://openalex.org/W2897949376","https://openalex.org/W2168953691","https://openalex.org/W2997891576","https://openalex.org/W2370875228","https://openalex.org/W2349838408","https://openalex.org/W2391957050","https://openalex.org/W2352065863"],"abstract_inverted_index":{"The":[0,13,79],"TF-IDF":[1,33],"algorithm":[2,34,81],"is":[3,82,119],"one":[4],"of":[5,10,16,74],"the":[6,31,103,108,111,125,133,136],"most":[7],"common":[8],"methods":[9,45],"text":[11,22,94],"representation.":[12],"basic":[14],"tasks":[15],"natural":[17],"language":[18],"processing,":[19],"for":[20,54,93],"example,":[21],"classification,":[23],"generally":[24],"use":[25,73],"it":[26,75,88,118],"to":[27,76,89,132],"represent":[28,90],"text.":[29],"However,":[30],"traditional":[32,134],"doesn't":[35],"work":[36],"well":[37],"and":[38,71,85,114],"has":[39],"many":[40,43],"shortcomings.":[41],"Actually,":[42],"improved":[44],"have":[46],"achieved":[47],"good":[48],"results,":[49],"but":[50],"they":[51],"are":[52],"ineffective":[53],"desensitized":[55,91,126],"data":[56,92],"or":[57],"encrypted":[58],"data.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,86],"propose":[64],"a":[65],"novel":[66],"notion,":[67],"class":[68],"discriminative":[69],"strength,":[70],"make":[72],"improve":[77],"TF-IDF.":[78],"new":[80],"named":[83],"TF-IDF-\u03c1":[84,137],"utilize":[87],"classification.":[95],"It's":[96],"worth":[97],"mentioning":[98],"that":[99],"experimental":[100],"results":[101],"from":[102],"validation":[104],"set,":[105],"such":[106],"as":[107],"recall":[109],"rate,":[110],"precision":[112],"rate":[113],"F1":[115,139],"measure,":[116],"illustrate":[117],"effective.":[120],"At":[121],"last,":[122],"experiments":[123],"on":[124],"test":[127],"set":[128],"indicate":[129],"that,":[130],"related":[131],"TF-IDF,":[135],"increase":[138],"measure":[140],"by":[141],"4.07%":[142],"at":[143],"most.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}