{"id":"https://openalex.org/W7166802079","doi":"https://doi.org/10.18653/v1/2026.smm4h-1.45","title":"MetaMiners at SMM4H-HeaRD 2026: A Semantic-Structural Knowledge-Enriched Ensemble for SARS-CoV-2 Metadata Identification","display_name":"MetaMiners at SMM4H-HeaRD 2026: A Semantic-Structural Knowledge-Enriched Ensemble for SARS-CoV-2 Metadata Identification","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166802079","doi":"https://doi.org/10.18653/v1/2026.smm4h-1.45"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.smm4h-1.45","doi":"https://doi.org/10.18653/v1/2026.smm4h-1.45","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.smm4h-1.45","pdf_url":"https://aclanthology.org/2026.smm4h-1.45.pdf","source":{"id":"https://openalex.org/S7407106391","display_name":"Social Media Mining for Health Research and Applications Workshop and Shared Tasks (SMM4H)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.smm4h-1.45.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139743793","display_name":"Claudia-Alexandra Ursu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Claudia-Alexandra Ursu","raw_affiliation_strings":["University of Bucharest"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bucharest","institution_ids":["https://openalex.org/I141595442"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139833239","display_name":"Alecsandru-Florin Soare","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Alecsandru-Florin Soare","raw_affiliation_strings":["University of Bucharest"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bucharest","institution_ids":["https://openalex.org/I141595442"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I141595442"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39903138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"272","last_page":"279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.6952999830245972,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.6952999830245972,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1420000046491623,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.0364999994635582,"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/pubmed-abstracts","display_name":"PubMed abstracts","score":0.7239999771118164},{"id":"https://openalex.org/keywords/imbalanced-binary-classification","display_name":"imbalanced binary classification","score":0.7419999837875366},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"ensemble learning","score":0.5839999914169312},{"id":"https://openalex.org/keywords/adversarial-training","display_name":"adversarial training","score":0.8889999985694885},{"id":"https://openalex.org/keywords/pubmedbert","display_name":"PubMedBERT","score":0.7620000243186951},{"id":"https://openalex.org/keywords/clinical-text-mining","display_name":"clinical text mining","score":0.3449999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006000280380249},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5216000080108643},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38100001215934753},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.24009999632835388},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2361000031232834}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.smm4h-1.45","doi":"https://doi.org/10.18653/v1/2026.smm4h-1.45","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.smm4h-1.45","pdf_url":"https://aclanthology.org/2026.smm4h-1.45.pdf","source":{"id":"https://openalex.org/S7407106391","display_name":"Social Media Mining for Health Research and Applications Workshop and Shared Tasks (SMM4H)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.smm4h-1.45","doi":"https://doi.org/10.18653/v1/2026.smm4h-1.45","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.smm4h-1.45","pdf_url":"https://aclanthology.org/2026.smm4h-1.45.pdf","source":{"id":"https://openalex.org/S7407106391","display_name":"Social Media Mining for Health Research and Applications Workshop and Shared Tasks (SMM4H)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.7246000170707703}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166802079.pdf","grobid_xml":"https://content.openalex.org/works/W7166802079.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4409875692","https://openalex.org/W7166882898","https://openalex.org/W4409655196","https://openalex.org/W7166869118","https://openalex.org/W4385798341","https://openalex.org/W3116099796","https://openalex.org/W4287519381","https://openalex.org/W3022143756","https://openalex.org/W4384926244","https://openalex.org/W4226367850"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,7,78,108,120],"hybrid":[4,79],"solution":[5,80,126],"for":[6,15],"binary":[8],"classification":[9],"of":[10,36,67,71,117],"medical":[11,61,72],"PubMed":[12],"articles":[13],"created":[14],"identifying":[16],"reports":[17,35,73],"that":[18,59,84],"associate":[19],"clinical":[20],"metadata":[21,39,44],"with":[22],"SARS-CoV-2":[23],"genomic":[24],"sequences.The":[25],"system":[26,76],"is":[27,45,56,63],"designed":[28],"to":[29,51,112],"catch":[30],"the":[31,57,60,125,131],"subtle":[32],"distinction":[33],"between":[34],"sequence-associated":[37],"patient":[38],"and":[40,93,123],"sentences":[41],"where":[42],"such":[43],"either":[46],"unrelated,":[47],"irrelevant,":[48],"or":[49],"linked":[50],"previous":[52],"studies.The":[53],"biggest":[54],"challenge":[55],"fact":[58],"dataset":[62],"highly":[64],"imbalanced,":[65],"consisting":[66],"only":[68],"13.3":[69],"%":[70],"labeled":[74],"positive.Our":[75],"proposes":[77],"combining":[81],"four":[82],"approaches":[83,97],"include":[85],"dual-evidence":[86],"tagging,":[87],"negation-aware":[88],"suppression,":[89],"semantic":[90],"frame":[91],"extraction,":[92],"adversarial":[94],"training.All":[95],"these":[96],"were":[98],"tested":[99],"on":[100],"multiple":[101],"models:":[102],"BiomedBERT-baseabstract,":[103],"BioLinkBERT-large,":[104],"PubMedBERTbase-fulltext,":[105],"followed":[106],"by":[107],"best-subset":[109],"ensemble":[110],"search":[111],"obtain":[113],"an":[114],"F1":[115],"score":[116],"0.786,":[118],"setting":[119],"new":[121],"benchmark":[122],"positioning":[124],"in":[127,130],"1st":[128],"place":[129],"competition.":[132]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-07-02T00:00:00"}