{"id":"https://openalex.org/W3186833834","doi":"https://doi.org/10.1109/access.2021.3099758","title":"Text Guide: Improving the Quality of Long Text Classification by a Text Selection Method Based on Feature Importance","display_name":"Text Guide: Improving the Quality of Long Text Classification by a Text Selection Method Based on Feature Importance","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3186833834","doi":"https://doi.org/10.1109/access.2021.3099758","mag":"3186833834"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3099758","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3099758","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09494560.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09494560.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061282814","display_name":"Krzysztof Fiok","orcid":"https://orcid.org/0000-0001-5711-1498"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Krzysztof Fiok","raw_affiliation_strings":["Department of Industrial Engineering and Management Systems, University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Management Systems, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068942141","display_name":"Waldemar Karwowski","orcid":"https://orcid.org/0000-0002-9134-3441"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Waldemar Karwowski","raw_affiliation_strings":["Department of Industrial Engineering and Management Systems, University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Management Systems, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056491924","display_name":"Edgar Guti\u00e9rrez-Franco","orcid":"https://orcid.org/0000-0002-8128-5356"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edgar Gutierrez-Franco","raw_affiliation_strings":["Center for Transportation and Logistics, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Transportation and Logistics, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076717526","display_name":"Mohammad Reza Davahli","orcid":"https://orcid.org/0000-0003-4021-1235"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Reza Davahli","raw_affiliation_strings":["Department of Industrial Engineering and Management Systems, University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Management Systems, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050791292","display_name":"Maciej Wilamowski","orcid":"https://orcid.org/0000-0001-8478-572X"},"institutions":[{"id":"https://openalex.org/I4654613","display_name":"University of Warsaw","ror":"https://ror.org/039bjqg32","country_code":"PL","type":"education","lineage":["https://openalex.org/I4654613"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Maciej Wilamowski","raw_affiliation_strings":["Faculty of Economic Sciences, University of Warsaw, Warsaw, Poland"],"affiliations":[{"raw_affiliation_string":"Faculty of Economic Sciences, University of Warsaw, Warsaw, Poland","institution_ids":["https://openalex.org/I4654613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110182411","display_name":"Tareq Ahram","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tareq Ahram","raw_affiliation_strings":["Department of Industrial Engineering and Management Systems, University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Management Systems, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076775181","display_name":"Awad M. Aljuaid","orcid":"https://orcid.org/0000-0002-3793-4814"},"institutions":[{"id":"https://openalex.org/I179331831","display_name":"Taif University","ror":"https://ror.org/014g1a453","country_code":"SA","type":"education","lineage":["https://openalex.org/I179331831"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Awad Al-Juaid","raw_affiliation_strings":["Department of Industrial Engineering, College of Engineering, Taif University, Ta’if, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering, College of Engineering, Taif University, Ta’if, Saudi Arabia","institution_ids":["https://openalex.org/I179331831"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042920527","display_name":"Jozef Zurada","orcid":"https://orcid.org/0000-0003-1633-3152"},"institutions":[{"id":"https://openalex.org/I142740786","display_name":"University of Louisville","ror":"https://ror.org/01ckdn478","country_code":"US","type":"education","lineage":["https://openalex.org/I142740786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jozef Zurada","raw_affiliation_strings":["Business School, University of Louisville, Louisville, KY, USA"],"affiliations":[{"raw_affiliation_string":"Business School, University of Louisville, Louisville, KY, USA","institution_ids":["https://openalex.org/I142740786"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5061282814"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.4996,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.93760956,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"9","issue":null,"first_page":"105439","last_page":"105450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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/T10028","display_name":"Topic Modeling","score":1.0,"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":0.9993000030517578,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9991999864578247,"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":0.8132296800613403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5550861954689026},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5545578598976135},{"id":"https://openalex.org/keywords/noisy-text-analytics","display_name":"Noisy text analytics","score":0.4770081043243408},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46306246519088745},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4355127811431885},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.43461501598358154},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36339735984802246},{"id":"https://openalex.org/keywords/text-graph","display_name":"Text graph","score":0.3439885973930359},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.3002298176288605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132296800613403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5550861954689026},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5545578598976135},{"id":"https://openalex.org/C151375590","wikidata":"https://www.wikidata.org/wiki/Q17147076","display_name":"Noisy text analytics","level":4,"score":0.4770081043243408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46306246519088745},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4355127811431885},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.43461501598358154},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36339735984802246},{"id":"https://openalex.org/C66945725","wikidata":"https://www.wikidata.org/wiki/Q18388823","display_name":"Text graph","level":3,"score":0.3439885973930359},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.3002298176288605},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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":3,"locations":[{"id":"doi:10.1109/access.2021.3099758","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3099758","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09494560.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2104.07225","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.07225","pdf_url":"https://arxiv.org/pdf/2104.07225","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:95251632594b470da62df0c74adbbe9f","is_oa":true,"landing_page_url":"https://doaj.org/article/95251632594b470da62df0c74adbbe9f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 105439-105450 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3099758","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3099758","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09494560.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1938846955","display_name":null,"funder_award_id":"TURSP-2020/22","funder_id":"https://openalex.org/F4320323722","funder_display_name":"Taif University"},{"id":"https://openalex.org/G2811237814","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4393481380","display_name":null,"funder_award_id":"Saudi Arabia","funder_id":"https://openalex.org/F4320323722","funder_display_name":"Taif University"},{"id":"https://openalex.org/G6624020838","display_name":null,"funder_award_id":"N000141812559","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6687795668","display_name":null,"funder_award_id":"N00014181255","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7205854134","display_name":null,"funder_award_id":"TURSP-2020/229","funder_id":"https://openalex.org/F4320323722","funder_display_name":"Taif University"},{"id":"https://openalex.org/G7299194679","display_name":null,"funder_award_id":"TURSP-2020","funder_id":"https://openalex.org/F4320323722","funder_display_name":"Taif University"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320310161","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12"},{"id":"https://openalex.org/F4320323722","display_name":"Taif University","ror":"https://ror.org/014g1a453"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3186833834.pdf","grobid_xml":"https://content.openalex.org/works/W3186833834.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W2153579005","https://openalex.org/W2406501289","https://openalex.org/W2489406233","https://openalex.org/W2945824677","https://openalex.org/W2946119234","https://openalex.org/W2962862931","https://openalex.org/W2963159735","https://openalex.org/W2963403868","https://openalex.org/W2965373594","https://openalex.org/W2970183009","https://openalex.org/W2980708516","https://openalex.org/W2982597744","https://openalex.org/W2994673210","https://openalex.org/W2996428491","https://openalex.org/W2997273179","https://openalex.org/W2999309192","https://openalex.org/W3015468748","https://openalex.org/W3045733172","https://openalex.org/W3085139254","https://openalex.org/W3091156754","https://openalex.org/W3103677861","https://openalex.org/W3103682594","https://openalex.org/W3121592593","https://openalex.org/W4287667694","https://openalex.org/W4287704453","https://openalex.org/W4294170691","https://openalex.org/W4295838474","https://openalex.org/W4309793872","https://openalex.org/W4385245566","https://openalex.org/W4398471692","https://openalex.org/W6682691769","https://openalex.org/W6736575291","https://openalex.org/W6737947904","https://openalex.org/W6739901393","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6770292678","https://openalex.org/W6771626834","https://openalex.org/W6776048684","https://openalex.org/W6781533629","https://openalex.org/W6783267081","https://openalex.org/W6783944145","https://openalex.org/W6785148927","https://openalex.org/W6785783668"],"related_works":["https://openalex.org/W2770471982","https://openalex.org/W2770474375","https://openalex.org/W2152349655","https://openalex.org/W4384067529","https://openalex.org/W2372183225","https://openalex.org/W1625494842","https://openalex.org/W2389119968","https://openalex.org/W4390515129","https://openalex.org/W2174664889","https://openalex.org/W2475935882"],"abstract_inverted_index":{"The":[0],"performance":[1,110,143,182,208],"of":[2,16,37,61,78,92,160,183],"text":[3,14,40,94,102,120,130,191],"classification":[4,49],"methods":[5],"has":[6,23],"improved":[7],"greatly":[8],"over":[9,144],"the":[10,33,58,62,70,75,89,97,128,158,166,181,203,214],"last":[11],"decade":[12],"for":[13,50,69,189],"instances":[15,103],"less":[17],"than":[18],"512":[19],"tokens.":[20],"This":[21],"limit":[22,137],"been":[24],"adopted":[25],"by":[26,225],"most":[27],"state-of-the-research":[28],"transformer":[29,80],"models":[30,186],"due":[31],"to":[32,47,56,99,134,179,205],"high":[34,109],"computational":[35,63,114,152],"cost":[36,64],"analyzing":[38],"longer":[39,51],"instances.":[41],"To":[42],"mitigate":[43],"this":[44,226],"problem":[45],"and":[46,65,146,209],"improve":[48,180],"texts,":[52],"researchers":[53],"have":[54,66],"sought":[55],"resolve":[57],"underlying":[59],"causes":[60],"proposed":[67],"optimizations":[68],"attention":[71],"mechanism,":[72],"which":[73,127],"is":[74,132,202,216],"key":[76,204],"element":[77],"every":[79],"model.":[81],"In":[82],"our":[83],"study,":[84],"we":[85,117,197],"are":[86],"not":[87],"pursuing":[88],"ultimate":[90],"goal":[91],"long":[93,190],"classification,":[95,192],"i.e.,":[96],"ability":[98],"analyze":[100],"entire":[101],"at":[104,111],"one":[105],"time":[106],"while":[107,149],"preserving":[108,150],"a":[112,119,135,139,163],"reasonable":[113],"cost.":[115],"Instead,":[116],"propose":[118],"truncation":[121],"method":[122,215],"called":[123],"Text":[124,154,174,206],"Guide,":[125],"in":[126,138],"original":[129],"length":[131],"reduced":[133],"predefined":[136],"manner":[140],"that":[141,173,199],"improves":[142],"naive":[145],"semi-naive":[147],"approaches":[148],"low":[151],"costs.":[153],"Guide":[155,175,207],"benefits":[156,223],"from":[157,165],"concept":[159],"feature":[161],"importance,":[162],"notion":[164],"explainable":[167],"artificial":[168],"intelligence":[169],"domain.":[170],"We":[171],"demonstrate":[172],"can":[176],"be":[177,211],"used":[178],"recent":[184],"language":[185],"specifically":[187],"designed":[188],"such":[193],"as":[194],"Longformer.":[195],"Moreover,":[196],"discovered":[198],"parameter":[200],"optimization":[201],"must":[210],"conducted":[212],"before":[213],"deployed.":[217],"Future":[218],"experiments":[219],"may":[220],"reveal":[221],"additional":[222],"provided":[224],"new":[227],"method.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-08-02T00:00:00"}