{"id":"https://openalex.org/W4281700637","doi":"https://doi.org/10.3233/shti220147","title":"Improving Keyword-Based Topic Classification in Cancer Patient Forums with Multilingual Transformers","display_name":"Improving Keyword-Based Topic Classification in Cancer Patient Forums with Multilingual Transformers","publication_year":2022,"publication_date":"2022-06-06","ids":{"openalex":"https://openalex.org/W4281700637","doi":"https://doi.org/10.3233/shti220147","pmid":"https://pubmed.ncbi.nlm.nih.gov/35673086"},"language":"en","primary_location":{"id":"doi:10.3233/shti220147","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti220147","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI220147","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI220147","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046058191","display_name":"Tommaso Mario Buonocore","orcid":"https://orcid.org/0000-0002-2887-088X"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"T.M. Buonocore","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090028219","display_name":"Enea Parimbelli","orcid":"https://orcid.org/0000-0003-0679-828X"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"E. Parimbelli","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069995691","display_name":"Lucia Sacchi","orcid":"https://orcid.org/0000-0002-1390-9825"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"L. Sacchi","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050932220","display_name":"Riccardo Bellazzi","orcid":"https://orcid.org/0000-0002-6974-9808"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"R. Bellazzi","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy","institution_ids":["https://openalex.org/I25217355"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088813698","display_name":"Laura del Campo-Albendea","orcid":"https://orcid.org/0000-0002-1940-4932"},"institutions":[{"id":"https://openalex.org/I4210127391","display_name":"Italian Association for Cancer Research","ror":"https://ror.org/02g2x7380","country_code":"IT","type":"funder","lineage":["https://openalex.org/I4210127391"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"L. del Campo","raw_affiliation_strings":["AIMAC, Italian Association of Cancer patients, relatives and friends, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"AIMAC, Italian Association of Cancer patients, relatives and friends, Rome, Italy","institution_ids":["https://openalex.org/I4210127391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018925225","display_name":"Silvana Quaglini","orcid":"https://orcid.org/0000-0002-4288-2561"},"institutions":[{"id":"https://openalex.org/I25217355","display_name":"University of Pavia","ror":"https://ror.org/00s6t1f81","country_code":"IT","type":"education","lineage":["https://openalex.org/I25217355"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"S. Quaglini","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy","institution_ids":["https://openalex.org/I25217355"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046058191"],"corresponding_institution_ids":["https://openalex.org/I25217355"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19670051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"290","issue":null,"first_page":"597","last_page":"601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9772999882698059,"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":0.9664999842643738,"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":0.7807048559188843},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5626219511032104},{"id":"https://openalex.org/keywords/reusability","display_name":"Reusability","score":0.4504738748073578},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44268637895584106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44055506587028503},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.431221604347229},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4258761703968048},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3517736792564392},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34104520082473755},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33112335205078125},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.10859176516532898}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807048559188843},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5626219511032104},{"id":"https://openalex.org/C137981799","wikidata":"https://www.wikidata.org/wiki/Q1369184","display_name":"Reusability","level":3,"score":0.4504738748073578},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44268637895584106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44055506587028503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.431221604347229},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4258761703968048},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3517736792564392},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34104520082473755},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33112335205078125},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.10859176516532898},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D004724","descriptor_name":"Endoscopy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004724","descriptor_name":"Endoscopy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004724","descriptor_name":"Endoscopy","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":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","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":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019303","descriptor_name":"Multilingualism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019303","descriptor_name":"Multilingualism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019303","descriptor_name":"Multilingualism","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti220147","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti220147","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI220147","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:35673086","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35673086","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}],"best_oa_location":{"id":"doi:10.3233/shti220147","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti220147","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI220147","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281700637.pdf","grobid_xml":"https://content.openalex.org/works/W4281700637.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1942498636","https://openalex.org/W2045881275","https://openalex.org/W2075122081","https://openalex.org/W2103707329","https://openalex.org/W2131744502","https://openalex.org/W2136075087","https://openalex.org/W2152311353","https://openalex.org/W2164385956","https://openalex.org/W2909803291","https://openalex.org/W2938224028","https://openalex.org/W2963341956","https://openalex.org/W2982424689","https://openalex.org/W3035032094","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4282938614","https://openalex.org/W2906929912","https://openalex.org/W2099755394","https://openalex.org/W2350686889","https://openalex.org/W1965839502","https://openalex.org/W2114764029","https://openalex.org/W2621742671","https://openalex.org/W2373101891","https://openalex.org/W2277606120","https://openalex.org/W2977447223"],"abstract_inverted_index":{"Online":[0],"forums":[1],"play":[2],"an":[3,28,52],"important":[4],"role":[5],"in":[6,127],"connecting":[7],"people":[8],"who":[9],"have":[10,57],"crossed":[11],"paths":[12],"with":[13,70,90],"cancer.":[14],"These":[15],"communities":[16],"create":[17],"networks":[18],"of":[19,31,73,99,121],"mutual":[20],"support":[21],"that":[22,34,81],"cover":[23],"different":[24],"cancer-related":[25],"topics,":[26,69],"containing":[27],"extensive":[29],"amount":[30],"heterogeneous":[32],"information":[33],"can":[35],"be":[36],"mined":[37],"to":[38,66,106],"get":[39],"useful":[40],"insights.":[41],"This":[42],"work":[43],"presents":[44],"a":[45],"case":[46],"study":[47],"where":[48],"users'":[49],"posts":[50],"from":[51],"Italian":[53],"cancer":[54],"patient":[55],"community":[56],"been":[58],"classified":[59],"combining":[60],"both":[61],"count-based":[62],"and":[63,77,102,109],"prediction-based":[64],"representations":[65,85],"identify":[67],"discussion":[68],"the":[71,96,100,104,119],"aim":[72],"improving":[74],"message":[75],"reviewing":[76],"filtering.":[78],"We":[79],"demonstrate":[80],"pairing":[82],"simple":[83],"bag-of-words":[84],"based":[86],"on":[87],"keywords":[88],"matching":[89],"pre-trained":[91],"contextual":[92],"embeddings":[93],"significantly":[94],"improves":[95],"overall":[97],"quality":[98],"predictions":[101],"allows":[103],"model":[105],"handle":[107],"ambiguities":[108],"misspellings.":[110],"By":[111],"using":[112],"non-English":[113],"real-world":[114],"data,":[115],"we":[116],"also":[117],"investigated":[118],"reusability":[120],"pretrained":[122],"multilingual":[123],"models":[124],"like":[125,131],"BERT":[126],"lower":[128],"data":[129],"regimes":[130],"many":[132],"local":[133],"medical":[134],"institutions.":[135]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
