{"id":"https://openalex.org/W4293086888","doi":"https://doi.org/10.1007/s10579-022-09588-2","title":"Predicting lexical complexity in English texts: the Complex 2.0 dataset","display_name":"Predicting lexical complexity in English texts: the Complex 2.0 dataset","publication_year":2022,"publication_date":"2022-03-23","ids":{"openalex":"https://openalex.org/W4293086888","doi":"https://doi.org/10.1007/s10579-022-09588-2"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-022-09588-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-022-09588-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-022-09588-2.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-022-09588-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035746903","display_name":"Matthew Shardlow","orcid":"https://orcid.org/0000-0003-1129-2750"},"institutions":[{"id":"https://openalex.org/I11983389","display_name":"Manchester Metropolitan University","ror":"https://ror.org/02hstj355","country_code":"GB","type":"education","lineage":["https://openalex.org/I11983389"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Matthew Shardlow","raw_affiliation_strings":["Manchester Metropolitan University, Manchester, UK"],"raw_orcid":"https://orcid.org/0000-0003-1129-2750","affiliations":[{"raw_affiliation_string":"Manchester Metropolitan University, Manchester, UK","institution_ids":["https://openalex.org/I11983389"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007426493","display_name":"Richard Evans","orcid":"https://orcid.org/0000-0002-1220-8605"},"institutions":[{"id":"https://openalex.org/I119664326","display_name":"University of Wolverhampton","ror":"https://ror.org/01k2y1055","country_code":"GB","type":"education","lineage":["https://openalex.org/I119664326"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard Evans","raw_affiliation_strings":["University of Wolverhampton, Wolverhampton, UK"],"raw_orcid":"https://orcid.org/0000-0002-1220-8605","affiliations":[{"raw_affiliation_string":"University of Wolverhampton, Wolverhampton, UK","institution_ids":["https://openalex.org/I119664326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024937008","display_name":"Marcos Zampieri","orcid":"https://orcid.org/0000-0002-2346-3847"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcos Zampieri","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, USA"],"raw_orcid":"https://orcid.org/0000-0002-2346-3847","affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, USA","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035746903"],"corresponding_institution_ids":["https://openalex.org/I11983389"],"apc_list":null,"apc_paid":null,"fwci":1.5264,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.85428388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"56","issue":"4","first_page":"1153","last_page":"1194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","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/T13629","display_name":"Text Readability and Simplification","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9939000010490417,"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":0.9743000268936157,"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":0.8177758455276489},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7240949273109436},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6631853580474854},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6448421478271484},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.6379204988479614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.619782567024231},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5196862816810608},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5099464654922485},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.46602723002433777},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.4265357255935669},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.4218060374259949},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35492509603500366},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11495131254196167},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.07497113943099976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8177758455276489},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7240949273109436},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6631853580474854},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6448421478271484},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.6379204988479614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.619782567024231},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5196862816810608},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5099464654922485},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46602723002433777},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4265357255935669},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.4218060374259949},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35492509603500366},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11495131254196167},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.07497113943099976},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10579-022-09588-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-022-09588-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-022-09588-2.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},{"id":"pmh:oai:e-space.mmu.ac.uk:629988","is_oa":false,"landing_page_url":"https://e-space.mmu.ac.uk/view/authors/0968113562b696ae8c7c83245403c676.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4306401617","display_name":"e-space (Manchester Metropolitan University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I11983389","host_organization_name":"Manchester Metropolitan University","host_organization_lineage":["https://openalex.org/I11983389"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:arXiv.org:2102.08773","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.08773","pdf_url":"https://arxiv.org/pdf/2102.08773","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:wlv.openrepository.com:2436/624697","is_oa":true,"landing_page_url":"http://hdl.handle.net/2436/624697","pdf_url":null,"source":{"id":"https://openalex.org/S4306401000","display_name":"Wolverhampton Intellectual Repository and E-Theses (University of Wolverhampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119664326","host_organization_name":"University of Wolverhampton","host_organization_lineage":["https://openalex.org/I119664326"],"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":"","raw_type":"Journal article"}],"best_oa_location":{"id":"doi:10.1007/s10579-022-09588-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-022-09588-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-022-09588-2.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4293086888.pdf","grobid_xml":"https://content.openalex.org/works/W4293086888.grobid-xml"},"referenced_works_count":85,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W98658220","https://openalex.org/W638675188","https://openalex.org/W1498763386","https://openalex.org/W1975170560","https://openalex.org/W1981352964","https://openalex.org/W1985953330","https://openalex.org/W1994502537","https://openalex.org/W1995514968","https://openalex.org/W2001152062","https://openalex.org/W2007780422","https://openalex.org/W2014234225","https://openalex.org/W2016274652","https://openalex.org/W2016648380","https://openalex.org/W2017433125","https://openalex.org/W2038392811","https://openalex.org/W2040298461","https://openalex.org/W2041532239","https://openalex.org/W2064600544","https://openalex.org/W2073679637","https://openalex.org/W2090489837","https://openalex.org/W2090696193","https://openalex.org/W2112282043","https://openalex.org/W2115888644","https://openalex.org/W2123442489","https://openalex.org/W2133990480","https://openalex.org/W2136525955","https://openalex.org/W2138401331","https://openalex.org/W2153982529","https://openalex.org/W2168745915","https://openalex.org/W2250365808","https://openalex.org/W2250539671","https://openalex.org/W2250845501","https://openalex.org/W2251681775","https://openalex.org/W2251814648","https://openalex.org/W2460985275","https://openalex.org/W2462529001","https://openalex.org/W2463861136","https://openalex.org/W2463901756","https://openalex.org/W2464252445","https://openalex.org/W2464284135","https://openalex.org/W2464597371","https://openalex.org/W2465261327","https://openalex.org/W2466282755","https://openalex.org/W2466608730","https://openalex.org/W2467743264","https://openalex.org/W2467800307","https://openalex.org/W2469576572","https://openalex.org/W2471229275","https://openalex.org/W2471939052","https://openalex.org/W2473134909","https://openalex.org/W2473360228","https://openalex.org/W2473989358","https://openalex.org/W2474537198","https://openalex.org/W2524789673","https://openalex.org/W2760797156","https://openalex.org/W2765169468","https://openalex.org/W2770960740","https://openalex.org/W2771588894","https://openalex.org/W2773955291","https://openalex.org/W2805180607","https://openalex.org/W2805197999","https://openalex.org/W2805222462","https://openalex.org/W2805807001","https://openalex.org/W2805927653","https://openalex.org/W2806175038","https://openalex.org/W2806198615","https://openalex.org/W2806926373","https://openalex.org/W2807091229","https://openalex.org/W2891244437","https://openalex.org/W2900122702","https://openalex.org/W2939860970","https://openalex.org/W2951520515","https://openalex.org/W2962948877","https://openalex.org/W2963510222","https://openalex.org/W2964174591","https://openalex.org/W2965979949","https://openalex.org/W3012348233","https://openalex.org/W3037554857","https://openalex.org/W3099585677","https://openalex.org/W3185421637","https://openalex.org/W4230097545","https://openalex.org/W6634627538","https://openalex.org/W6779083980","https://openalex.org/W7082766458"],"related_works":["https://openalex.org/W2394602299","https://openalex.org/W1539050421","https://openalex.org/W4200090029","https://openalex.org/W2741700407","https://openalex.org/W2916894319","https://openalex.org/W1563147278","https://openalex.org/W326721179","https://openalex.org/W2251387359","https://openalex.org/W2624106077","https://openalex.org/W2157036556"],"abstract_inverted_index":{"Abstract":[0],"Identifying":[1],"words":[2,64,151],"which":[3,63],"may":[4],"cause":[5],"difficulty":[6],"for":[7,29,94,100,146],"a":[8,34,52,98,111,135,154,160],"reader":[9],"is":[10,38,48,144],"an":[11,140],"essential":[12],"step":[13],"in":[14,62,84],"most":[15],"lexical":[16,22,104,130],"text":[17],"simplification":[18],"systems":[19],"prior":[20],"to":[21,41,109,125,153,167],"substitution":[23],"and":[24,47,65,87,106,122],"can":[25],"also":[26],"be":[27],"used":[28],"assessing":[30],"the":[31,89,101,127,148,169],"readability":[32],"of":[33,91,103,129,150,171],"text.":[35],"This":[36],"task":[37,86,170],"commonly":[39],"referred":[40],"as":[42,51],"complex":[43],"word":[44],"identification":[45],"(CWI)":[46],"often":[49],"modelled":[50],"supervised":[53],"classification":[54],"problem.":[55],"For":[56],"training":[57],"such":[58],"systems,":[59],"annotated":[60],"datasets":[61,93,124],"sometimes":[66],"multi-word":[67],"expressions":[68],"are":[69,73],"labelled":[70],"regarding":[71],"complexity":[72,105,149],"required.":[74],"In":[75],"this":[76,85,108],"paper":[77],"we":[78],"analyze":[79],"previous":[80],"work":[81],"carried":[82],"out":[83],"investigate":[88,126],"properties":[90],"CWI":[92],"English.":[95],"We":[96,116,132,158],"develop":[97],"protocol":[99,138,166],"annotation":[102,137,156],"use":[107],"annotate":[110],"new":[112,121,161,165],"dataset,":[113],"CompLex":[114],"2.0.":[115],"present":[117],"experiments":[118],"using":[119,163],"both":[120],"old":[123],"nature":[128],"complexity.":[131],"found":[133],"that":[134,143],"Likert-scale":[136],"provides":[139],"objective":[141],"setting":[142],"superior":[145],"identifying":[147],"compared":[152],"binary":[155],"protocol.":[157],"release":[159],"dataset":[162],"our":[164],"promote":[168],"Lexical":[172],"Complexity":[173],"Prediction.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-30T09:04:40.226872","created_date":"2025-10-10T00:00:00"}