{"id":"https://openalex.org/W6888027465","doi":"https://doi.org/10.18420/inf2024_36","title":"Assessing Large Language Models for annotating data in Dementia-Related texts: A Comparative Study with Human Annotators","display_name":"Assessing Large Language Models for annotating data in Dementia-Related texts: A Comparative Study with Human Annotators","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W6888027465","doi":"https://doi.org/10.18420/inf2024_36"},"language":"en","primary_location":{"id":"doi:10.18420/inf2024_36","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_36","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/inf2024_36","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Suravee, Sumaiya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suravee, Sumaiya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Stoev, Teodor","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stoev, Teodor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Konow, Sara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konow, Sara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yordanova, Kristina","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yordanova, Kristina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38014501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.24729999899864197,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T12488","display_name":"Mental Health via Writing","score":0.24729999899864197,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/T10028","display_name":"Topic Modeling","score":0.19259999692440033,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.08990000188350677,"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/annotation","display_name":"Annotation","score":0.8873000144958496},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4643000066280365},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.44920000433921814},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4088999927043915},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3407000005245209},{"id":"https://openalex.org/keywords/keyword-extraction","display_name":"Keyword extraction","score":0.28220000863075256}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8873000144958496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534999847412109},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6132000088691711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5619000196456909},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.44920000433921814},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4088999927043915},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.350600004196167},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C2780288562","wikidata":"https://www.wikidata.org/wiki/Q25053353","display_name":"Keyword extraction","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C2780790391","wikidata":"https://www.wikidata.org/wiki/Q1149626","display_name":"Written language","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18420/inf2024_36","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_36","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18420/inf2024_36","is_oa":true,"landing_page_url":"https://doi.org/10.18420/inf2024_36","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"the":[1,5,13,25,74,92,124,159,168,176,200,207],"aging":[2],"population":[3],"grows,":[4],"incidence":[6],"of":[7,15,39,94,132,137,140,209],"dementia":[8],"is":[9,43,52,55,196],"rising":[10],"sharply,":[11],"necessitating":[12],"extraction":[14],"domain-specific":[16,83],"information":[17],"from":[18,135],"texts":[19,104,134],"to":[20,87,198],"gain":[21],"valuable":[22],"insights":[23],"into":[24],"condition.":[26],"Training":[27],"Natural":[28],"Language":[29,61],"Processing":[30],"(NLP)":[31],"models":[32],"for":[33,185],"this":[34],"purpose":[35],"requires":[36],"substantial":[37],"amounts":[38],"annotated":[40,210],"data,":[41],"which":[42],"typically":[44],"produced":[45,111],"by":[46,105,112],"human":[47,50,113,127,169,203],"annotators.":[48,114],"While":[49],"annotation":[51,75,119,177],"precise,":[53],"it":[54,195],"also":[56],"labor-intensive":[57],"and":[58,72,99,121,126,155,205],"costly.":[59],"Large":[60],"Models":[62],"(LLMs)":[63],"present":[64],"a":[65,117,130,147],"promising":[66],"alternative":[67],"that":[68],"could":[69],"potentially":[70,85],"streamline":[71],"economize":[73],"process.":[76],"However,":[77],"LLMs":[78,95,172],"may":[79],"struggle":[80],"with":[81,109,142,158],"complex,":[82],"contexts,":[84],"leading":[86],"inaccuracies.":[88],"This":[89],"paper":[90],"investigates":[91],"effectiveness":[93],"in":[96,101,150],"annotating":[97],"words":[98],"phrases":[100],"ambiguous":[102],"dementia-related":[103],"comparing":[106],"LLM-generated":[107,190],"annotations":[108],"those":[110],"We":[115],"followed":[116],"specific":[118],"scheme":[120],"had":[122],"both":[123],"LLM":[125,154,160],"raters":[128,204],"annotate":[129],"corpus":[131],"informal":[133],"forums":[136],"family":[138],"carers":[139],"people":[141],"dementia.":[143],"The":[144],"results":[145],"indicate":[146],"moderate":[148],"overlap":[149],"inter-rater":[151],"agreement":[152],"between":[153],"expert":[156,193],"annotators,":[157],"identifying":[161],"nearly":[162],"twice":[163],"as":[164,167],"many":[165],"instances":[166],"raters.":[170],"Although":[171],"can":[173],"partially":[174],"automate":[175],"process,":[178],"they":[179],"are":[180],"not":[181],"yet":[182],"fully":[183],"reliable":[184],"complex":[186],"domains.":[187],"By":[188],"refining":[189],"data":[191],"through":[192],"review,":[194],"possible":[197],"reduce":[199],"burden":[201],"on":[202],"accelerate":[206],"creation":[208],"datasets.":[211]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}