{"id":"https://openalex.org/W4391224989","doi":"https://doi.org/10.3233/shti230937","title":"A Five-Step Workflow to Manually Annotate Unstructured Data into Training Dataset for Natural Language Processing","display_name":"A Five-Step Workflow to Manually Annotate Unstructured Data into Training Dataset for Natural Language Processing","publication_year":2024,"publication_date":"2024-01-25","ids":{"openalex":"https://openalex.org/W4391224989","doi":"https://doi.org/10.3233/shti230937","pmid":"https://pubmed.ncbi.nlm.nih.gov/38269775"},"language":"en","primary_location":{"id":"doi:10.3233/shti230937","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti230937","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230937","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230937","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013214798","display_name":"Yunshu Zhu","orcid":"https://orcid.org/0000-0003-2786-0775"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yunshu Zhu","raw_affiliation_strings":["Centre for Digital Transformation, School of Computing and Information Technology, University of Wollongong, Wollongong, New South Wales, Australia"],"raw_orcid":"https://orcid.org/0000-0003-2786-0775","affiliations":[{"raw_affiliation_string":"Centre for Digital Transformation, School of Computing and Information Technology, University of Wollongong, Wollongong, New South Wales, Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705757","display_name":"Ting Song","orcid":"https://orcid.org/0000-0001-5858-6495"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ting Song","raw_affiliation_strings":["Centre for Digital Transformation, School of Computing and Information Technology, University of Wollongong, Wollongong, New South Wales, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5858-6495","affiliations":[{"raw_affiliation_string":"Centre for Digital Transformation, School of Computing and Information Technology, University of Wollongong, Wollongong, New South Wales, Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714729","display_name":"Zhenyu Zhang","orcid":"https://orcid.org/0000-0003-1853-4978"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhang","raw_affiliation_strings":["Centre for Digital Transformation, School of Computing and Information Technology, University of Wollongong, Wollongong, New South Wales, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1853-4978","affiliations":[{"raw_affiliation_string":"Centre for Digital Transformation, School of Computing and Information Technology, University of Wollongong, Wollongong, New South Wales, Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039340547","display_name":"Mengyang Yin","orcid":"https://orcid.org/0000-0002-0212-4598"},"institutions":[{"id":"https://openalex.org/I4210129032","display_name":"Adventist HealthCare","ror":"https://ror.org/039d9wk42","country_code":"AU","type":"healthcare","lineage":["https://openalex.org/I4210129032"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mengyang Yin","raw_affiliation_strings":["Opal Healthcare, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0212-4598","affiliations":[{"raw_affiliation_string":"Opal Healthcare, Sydney, Australia","institution_ids":["https://openalex.org/I4210129032"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064032702","display_name":"Ping Yu","orcid":"https://orcid.org/0000-0002-7910-9396"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]},{"id":"https://openalex.org/I4210129032","display_name":"Adventist HealthCare","ror":"https://ror.org/039d9wk42","country_code":"AU","type":"healthcare","lineage":["https://openalex.org/I4210129032"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ping Yu","raw_affiliation_strings":["Centre for Digital Transformation, School of Computing and Information Technology, University of Wollongong, Wollongong, New South Wales, Australia","Opal Healthcare, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7910-9396","affiliations":[{"raw_affiliation_string":"Centre for Digital Transformation, School of Computing and Information Technology, University of Wollongong, Wollongong, New South Wales, Australia","institution_ids":["https://openalex.org/I204824540"]},{"raw_affiliation_string":"Opal Healthcare, Sydney, Australia","institution_ids":["https://openalex.org/I4210129032"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7645,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8981914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"310","issue":null,"first_page":"109","last_page":"113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9768000245094299,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9768000245094299,"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/T12790","display_name":"Nursing Diagnosis and Documentation","score":0.9614999890327454,"subfield":{"id":"https://openalex.org/subfields/2910","display_name":"Issues, ethics and legal aspects"},"field":{"id":"https://openalex.org/fields/29","display_name":"Nursing"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8620285987854004},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8181407451629639},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7253979444503784},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6332080364227295},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5938429832458496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5781674385070801},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5524385571479797},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.5170015096664429},{"id":"https://openalex.org/keywords/controlled-vocabulary","display_name":"Controlled vocabulary","score":0.45876187086105347},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44957435131073},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.42509639263153076},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19395491480827332},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.15397632122039795},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.12879925966262817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8620285987854004},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8181407451629639},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7253979444503784},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6332080364227295},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5938429832458496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5781674385070801},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5524385571479797},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.5170015096664429},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.45876187086105347},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44957435131073},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.42509639263153076},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19395491480827332},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.15397632122039795},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.12879925966262817},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000368","descriptor_name":"Aged","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000368","descriptor_name":"Aged","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000368","descriptor_name":"Aged","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001315","descriptor_name":"Australia","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001315","descriptor_name":"Australia","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001315","descriptor_name":"Australia","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057188","descriptor_name":"Workflow","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057286","descriptor_name":"Electronic Health Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.3233/shti230937","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti230937","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230937","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:38269775","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38269775","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in health technology and informatics","raw_type":null},{"id":"pmh:oai:ro.uow.edu.au:test2021-15986","is_oa":true,"landing_page_url":"https://doi.org/10.3233/SHTI230937","pdf_url":null,"source":{"id":"https://openalex.org/S4306400510","display_name":"Research Online (University of Wollongong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I204824540","host_organization_name":"University of Wollongong","host_organization_lineage":["https://openalex.org/I204824540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus Harvesting Series","raw_type":"text"},{"id":"doi:10.71747/uow-r3gk326m.29826971","is_oa":true,"landing_page_url":"https://doi.org/10.71747/uow-r3gk326m.29826971","pdf_url":null,"source":{"id":"https://openalex.org/S4306400510","display_name":"Research Online (University of Wollongong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I204824540","host_organization_name":"University of Wollongong","host_organization_lineage":["https://openalex.org/I204824540"],"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"},{"id":"doi:10.71747/uow-r3gk326m.29826971.v1","is_oa":true,"landing_page_url":"https://doi.org/10.71747/uow-r3gk326m.29826971.v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400510","display_name":"Research Online (University of Wollongong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I204824540","host_organization_name":"University of Wollongong","host_organization_lineage":["https://openalex.org/I204824540"],"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"}],"best_oa_location":{"id":"doi:10.3233/shti230937","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti230937","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI230937","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391224989.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2071890384","https://openalex.org/W2768488789","https://openalex.org/W2888255003","https://openalex.org/W2889860923","https://openalex.org/W2912971066","https://openalex.org/W2941773520","https://openalex.org/W3081579774","https://openalex.org/W3112428616","https://openalex.org/W3139761694","https://openalex.org/W3162707446","https://openalex.org/W3207819469","https://openalex.org/W4220726160","https://openalex.org/W4221081696","https://openalex.org/W4303685093"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W4377865234","https://openalex.org/W2032702205"],"abstract_inverted_index":{"Natural":[0],"Language":[1],"Processing":[2],"(NLP)":[3],"is":[4,23,33],"a":[5,19,34,58],"powerful":[6],"technique":[7],"for":[8,21,61,138],"extracting":[9],"valuable":[10],"information":[11],"from":[12,99],"unstructured":[13,47,64,101],"electronic":[14],"health":[15],"records":[16],"(EHRs).":[17],"However,":[18],"prerequisite":[20],"NLP":[22,52,140],"the":[24,41,73,100],"availability":[25],"of":[26,36,44,103,117],"high-quality":[27],"annotated":[28,111,135],"datasets.":[29],"To":[30],"date,":[31],"there":[32],"lack":[35],"effective":[37],"methods":[38],"to":[39,95,133],"guide":[40],"research":[42],"effort":[43],"manually":[45,62],"annotating":[46,63],"datasets,":[48,65],"which":[49],"can":[50,126],"hinder":[51],"performance.":[53],"Therefore,":[54],"this":[55],"study":[56],"develops":[57],"five-step":[59],"workflow":[60,125],"including":[66],"(1)":[67],"annotator":[68],"training":[69,136],"and":[70,86],"familiarising":[71],"with":[72],"text":[74],"corpus,":[75],"(2)":[76],"vocabulary":[77],"identification,":[78],"(3)":[79],"annotation":[80,84,124],"schema":[81],"development,":[82],"(4)":[83],"execution,":[85],"(5)":[87],"result":[88],"validation.":[89],"This":[90,119],"framework":[91],"was":[92],"then":[93],"applied":[94],"annotate":[96],"agitation":[97],"symptoms":[98],"EHRs":[102],"40":[104],"Australian":[105],"residential":[106],"aged":[107],"care":[108],"facilities.":[109],"The":[110],"corpus":[112,137],"achieved":[113],"an":[114],"accuracy":[115],"rate":[116],"96%.":[118],"suggests":[120],"that":[121],"our":[122],"proposed":[123],"be":[127],"used":[128],"in":[129],"manual":[130],"data":[131],"processing":[132],"develop":[134],"developing":[139],"algorithms.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2024-01-26T00:00:00"}
