{"id":"https://openalex.org/W4393082356","doi":"https://doi.org/10.3390/a17040132","title":"The Impact of Data Preparation and Model Complexity on the Natural Language Classification of Chinese News Headlines","display_name":"The Impact of Data Preparation and Model Complexity on the Natural Language Classification of Chinese News Headlines","publication_year":2024,"publication_date":"2024-03-22","ids":{"openalex":"https://openalex.org/W4393082356","doi":"https://doi.org/10.3390/a17040132"},"language":"en","primary_location":{"id":"doi:10.3390/a17040132","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17040132","pdf_url":"https://www.mdpi.com/1999-4893/17/4/132/pdf?version=1711103523","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/17/4/132/pdf?version=1711103523","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086778517","display_name":"Torrey Wagner","orcid":"https://orcid.org/0000-0002-1039-1055"},"institutions":[{"id":"https://openalex.org/I55061410","display_name":"U.S. Air Force Institute of Technology","ror":"https://ror.org/03f9f1d95","country_code":"US","type":"education","lineage":["https://openalex.org/I1294991024","https://openalex.org/I1330347796","https://openalex.org/I1330347796","https://openalex.org/I2802362820","https://openalex.org/I4210089612","https://openalex.org/I4210102105","https://openalex.org/I4210102105","https://openalex.org/I55061410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Torrey Wagner","raw_affiliation_strings":["Data Analytics Certificate Program, Graduate School of Engineering and Management, Air Force Institute of Technology, Wright-Patterson AFB, OH 45433, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Analytics Certificate Program, Graduate School of Engineering and Management, Air Force Institute of Technology, Wright-Patterson AFB, OH 45433, USA","institution_ids":["https://openalex.org/I55061410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094221264","display_name":"Dennis Guhl","orcid":null},"institutions":[{"id":"https://openalex.org/I55061410","display_name":"U.S. Air Force Institute of Technology","ror":"https://ror.org/03f9f1d95","country_code":"US","type":"education","lineage":["https://openalex.org/I1294991024","https://openalex.org/I1330347796","https://openalex.org/I1330347796","https://openalex.org/I2802362820","https://openalex.org/I4210089612","https://openalex.org/I4210102105","https://openalex.org/I4210102105","https://openalex.org/I55061410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dennis Guhl","raw_affiliation_strings":["Data Analytics Certificate Program, Graduate School of Engineering and Management, Air Force Institute of Technology, Wright-Patterson AFB, OH 45433, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Analytics Certificate Program, Graduate School of Engineering and Management, Air Force Institute of Technology, Wright-Patterson AFB, OH 45433, USA","institution_ids":["https://openalex.org/I55061410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015438083","display_name":"Brent Langhals","orcid":"https://orcid.org/0000-0002-8952-7778"},"institutions":[{"id":"https://openalex.org/I55061410","display_name":"U.S. Air Force Institute of Technology","ror":"https://ror.org/03f9f1d95","country_code":"US","type":"education","lineage":["https://openalex.org/I1294991024","https://openalex.org/I1330347796","https://openalex.org/I1330347796","https://openalex.org/I2802362820","https://openalex.org/I4210089612","https://openalex.org/I4210102105","https://openalex.org/I4210102105","https://openalex.org/I55061410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brent Langhals","raw_affiliation_strings":["Data Analytics Certificate Program, Graduate School of Engineering and Management, Air Force Institute of Technology, Wright-Patterson AFB, OH 45433, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Analytics Certificate Program, Graduate School of Engineering and Management, Air Force Institute of Technology, Wright-Patterson AFB, OH 45433, USA","institution_ids":["https://openalex.org/I55061410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5086778517"],"corresponding_institution_ids":["https://openalex.org/I55061410"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1782},"fwci":0.4869,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69055067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"17","issue":"4","first_page":"132","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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":0.9980000257492065,"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":0.6823108196258545},{"id":"https://openalex.org/keywords/chinese-language","display_name":"Chinese language","score":0.4964621663093567},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46104830503463745},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45316827297210693},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22741469740867615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6823108196258545},{"id":"https://openalex.org/C3018428822","wikidata":"https://www.wikidata.org/wiki/Q7850","display_name":"Chinese language","level":2,"score":0.4964621663093567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46104830503463745},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45316827297210693},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22741469740867615},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/a17040132","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17040132","pdf_url":"https://www.mdpi.com/1999-4893/17/4/132/pdf?version=1711103523","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:357191fbd054452d8cb6b0153ffad362","is_oa":true,"landing_page_url":"https://doaj.org/article/357191fbd054452d8cb6b0153ffad362","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 17, Iss 4, p 132 (2024)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-4893/17/4/132/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/a17040132","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/a17040132","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a17040132","pdf_url":"https://www.mdpi.com/1999-4893/17/4/132/pdf?version=1711103523","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4393082356.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W2170505850","https://openalex.org/W2487770199","https://openalex.org/W2803813753","https://openalex.org/W2996264288","https://openalex.org/W3034405584","https://openalex.org/W3034999214","https://openalex.org/W3096650070","https://openalex.org/W3114651185","https://openalex.org/W3122722952","https://openalex.org/W3135886602","https://openalex.org/W3165298146","https://openalex.org/W3165444985","https://openalex.org/W3198578829","https://openalex.org/W4225976419","https://openalex.org/W4303649216","https://openalex.org/W4319594527","https://openalex.org/W4386933640","https://openalex.org/W4394596872","https://openalex.org/W4394597209","https://openalex.org/W6757817989","https://openalex.org/W6781905506","https://openalex.org/W6810201887","https://openalex.org/W6849200219"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Given":[0],"the":[1,12,33,36,39,57,72,93,114,137,145,151,181,188,204,210,219,227],"emergence":[2],"of":[3,32,35,41,87,96,143,167],"China":[4],"as":[5],"a":[6,110,165,198],"political":[7],"and":[8,133,140,169,224],"economic":[9],"power":[10],"in":[11,19,29,215,218],"21st":[13],"century,":[14],"there":[15],"is":[16,191,202,226],"increased":[17],"interest":[18],"analyzing":[20],"Chinese":[21],"news":[22,43],"articles":[23,44,58],"to":[24,55,81,158,162,175],"better":[25],"understand":[26],"developing":[27],"trends":[28],"China.":[30],"Because":[31],"volume":[34],"material,":[37],"automating":[38,144],"categorization":[40,146],"Chinese-language":[42],"by":[45,164],"headline":[46],"text":[47],"or":[48],"titles":[49],"can":[50],"be":[51,180,209],"an":[52],"effective":[53],"way":[54],"sort":[56],"into":[59],"categories":[60,70],"for":[61,184,194],"efficient":[62],"review.":[63],"A":[64],"383,000-headline":[65],"dataset":[66,221],"labeled":[67],"with":[68,231],"15":[69],"from":[71],"Toutiao":[73,220],"website":[74],"was":[75,99,149,160],"evaluated":[76],"via":[77],"natural":[78],"language":[79],"processing":[80],"predict":[82,163],"topic":[83],"categories.":[84],"The":[85,101,125],"influence":[86],"six":[88],"data":[89,128],"preparation":[90,129],"variations":[91],"on":[92,109],"predictive":[94],"accuracy":[95,108,190],"four":[97,216],"algorithms":[98],"studied.":[100],"simplest":[102],"model":[103,117,153],"(Na\u00efve":[104],"Bayes)":[105],"achieved":[106],"85.1%":[107],"holdout":[111],"dataset,":[112],"while":[113],"most":[115,126],"complex":[116],"(Neural":[118],"Network":[119],"using":[120],"BERT)":[121],"demonstrated":[122],"89.3%":[123],"accuracy.":[124],"useful":[127],"steps":[130],"were":[131],"identified,":[132],"another":[134],"goal":[135],"examined":[136],"underlying":[138],"complexity":[139],"computational":[141],"costs":[142],"process.":[147],"It":[148],"discovered":[150],"BERT":[152],"required":[154,170],"170x":[155],"more":[156,172],"time":[157],"train,":[159],"slower":[161],"factor":[166],"18,600,":[168],"27x":[171],"disk":[173],"space":[174],"save,":[176],"indicating":[177],"it":[178],"may":[179],"best":[182,211],"choice":[183],"low-volume":[185],"applications":[186],"when":[187],"highest":[189],"needed.":[192],"However,":[193],"larger-scale":[195],"operations":[196],"where":[197],"slight":[199],"performance":[200],"degradation":[201],"tolerated,":[203],"Na\u00efve":[205],"Bayes":[206],"algorithm":[207],"could":[208],"choice.":[212],"Nearly":[213],"one":[214],"records":[217],"are":[222],"duplicates,":[223],"this":[225],"first":[228],"published":[229],"analysis":[230],"duplicates":[232],"removed.":[233]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
