{"id":"https://openalex.org/W7225617469","doi":"https://doi.org/10.21203/rs.3.rs-11114792/v1","title":"Development of a General Academic Written Chinese Word List: A Corpus-Based Approach","display_name":"Development of a General Academic Written Chinese Word List: A Corpus-Based Approach","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225617469","doi":"https://doi.org/10.21203/rs.3.rs-11114792/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11114792/v1","doi":"https://doi.org/10.21203/rs.3.rs-11114792/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11114792/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21203/rs.3.rs-11114792/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161359886","display_name":"Yeting Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I44675526","display_name":"Shanghai Ocean University","ror":"https://ror.org/04n40zv07","country_code":"CN","type":"education","lineage":["https://openalex.org/I44675526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yeting Jiang","raw_affiliation_strings":["Shanghai Ocean University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Ocean University","institution_ids":["https://openalex.org/I44675526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010444749","display_name":"Angkana Tongpoon-Patanasorn","orcid":"https://orcid.org/0000-0003-0035-8451","observed_orcids":["https://orcid.org/0000-0003-0035-8451"]},"institutions":[{"id":"https://openalex.org/I179193067","display_name":"Khon Kaen University","ror":"https://ror.org/03cq4gr50","country_code":"TH","type":"education","lineage":["https://openalex.org/I179193067"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Angkana Tongpoon-Patanasorn","raw_affiliation_strings":["Khon Kaen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khon Kaen University","institution_ids":["https://openalex.org/I179193067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11587","display_name":"Second Language Acquisition and Learning","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11587","display_name":"Second Language Acquisition and Learning","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12881","display_name":"linguistics and terminology studies","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12353","display_name":"Lexicography and Language Studies","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.8429999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6274999976158142},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5582000017166138},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.53329998254776},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4708000123500824},{"id":"https://openalex.org/C119867837","wikidata":"https://www.wikidata.org/wiki/Q4119870","display_name":"Academic writing","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.4505000114440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43299999833106995},{"id":"https://openalex.org/C49898467","wikidata":"https://www.wikidata.org/wiki/Q1517706","display_name":"Stratified sampling","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C2993275117","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word list","level":3,"score":0.4068000018596649},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.3801000118255615},{"id":"https://openalex.org/C62737587","wikidata":"https://www.wikidata.org/wiki/Q7939179","display_name":"Vocabulary development","level":3,"score":0.36660000681877136},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.32679998874664307},{"id":"https://openalex.org/C2778498041","wikidata":"https://www.wikidata.org/wiki/Q915466","display_name":"Academic year","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3107999861240387},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C2983335612","wikidata":"https://www.wikidata.org/wiki/Q54277","display_name":"Word processing","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C2776725116","wikidata":"https://www.wikidata.org/wiki/Q236935","display_name":"British National Corpus","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C120912362","wikidata":"https://www.wikidata.org/wiki/Q136822","display_name":"Higher education","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C8795937","wikidata":"https://www.wikidata.org/wiki/Q11862829","display_name":"Discipline","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11114792/v1","doi":"https://doi.org/10.21203/rs.3.rs-11114792/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11114792/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11114792/v1","doi":"https://doi.org/10.21203/rs.3.rs-11114792/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11114792/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"This":[1],"study":[2],"developed":[3],"the":[4,89,96,104,120,142,167,171,185],"General":[5,105],"Academic":[6,20,98,106],"Written":[7],"Chinese":[8,18,97,107],"Word":[9,48],"List":[10,100,109],"(GAWCWL)":[11],"as":[12],"a":[13,51,132,160,178],"supplementary":[14,139],"vocabulary":[15,112,182],"resource":[16],"for":[17,19,84,95,103,181],"Purposes":[21],"(CAP).":[22],"A":[23],"9.95-million-token":[24],"corpus":[25,151],"was":[26,113],"compiled":[27],"through":[28],"stratified":[29],"random":[30],"sampling":[31],"of":[32,60,86,134,136,146,152],"texts":[33,173],"published":[34],"between":[35],"2012":[36],"and":[37,42,69,72,82,101,157,196],"2022":[38],"across":[39],"ten":[40],"disciplines":[41],"four":[43,121],"written":[44,190],"academic":[45,168,191],"text":[46,122],"types.":[47],"selection":[49],"used":[50],"five-dimensional":[52],"procedure:":[53],"Jieba":[54],"segmentation":[55],"(candidate":[56],"extraction),":[57],"full":[58],"exclusion":[59],"Hanyu":[61],"Shuiping":[62],"Kaoshi":[63],"(HSK)":[64],"Levels":[65],"1\u20136":[66],"words,":[67],"frequency":[68],"range":[70],"thresholds,":[71],"Discipline":[73],"Measurement":[74],"(DM).":[75],"The":[76,175],"resulting":[77],"list":[78],"contained":[79],"487":[80],"entries":[81],"accounted":[83],"8.58%":[85],"tokens":[87,147],"in":[88,148,159,166,170,189],"development":[90],"corpus,":[91,162],"compared":[92],"with":[93,131],"7.66%":[94],"Vocabulary":[99,108],"4.86%":[102],"after":[110],"HSK":[111,187],"excluded":[114],"from":[115,127],"all":[116],"three":[117],"lists.":[118],"Across":[119],"types,":[123],"GAWCWL":[124,143,176],"coverage":[125,165],"ranged":[126],"7.22%":[128],"to":[129],"9.56%,":[130],"coefficient":[133],"variation":[135],"12.2%.":[137],"In":[138],"external":[140],"evaluation,":[141],"covered":[144],"8.79%":[145],"an":[149],"independent":[150],"aquatic":[153],"science":[154],"journal":[155],"articles":[156],"2.74%":[158],"science-fiction":[161],"indicating":[163],"higher":[164],"than":[169],"non-academic":[172],"examined.":[174],"provides":[177],"corpus-informed":[179],"reference":[180],"support":[183],"beyond":[184],"specified":[186],"baseline":[188],"Chinese.":[192],"Its":[193],"broader":[194],"applicability":[195],"instructional":[197],"effectiveness":[198],"require":[199],"further":[200],"investigation.":[201]},"counts_by_year":[],"updated_date":"2026-11-10T13:44:29.811591","created_date":"2026-11-10T00:00:00"}
