{"id":"https://openalex.org/W7129013445","doi":"https://doi.org/10.22541/au.177123975.54573004/v1","title":"Leveraging Transformer-Based Models for Post-Market Surveillance: A Case Study on Turkish E-Commerce Reviews of Diabetes Management Devices","display_name":"Leveraging Transformer-Based Models for Post-Market Surveillance: A Case Study on Turkish E-Commerce Reviews of Diabetes Management Devices","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129013445","doi":"https://doi.org/10.22541/au.177123975.54573004/v1"},"language":"en","primary_location":{"id":"doi:10.22541/au.177123975.54573004/v1","doi":"https://doi.org/10.22541/au.177123975.54573004/v1","is_oa":true,"landing_page_url":"https://doi.org/10.22541/au.177123975.54573004/v1","pdf_url":"https://www.authorea.com/doi/pdf/10.22541/au.177123975.54573004","source":null,"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.authorea.com/doi/pdf/10.22541/au.177123975.54573004","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011817420","display_name":"Emrah At\u0131lgan","orcid":"https://orcid.org/0000-0002-0395-9976","observed_orcids":["https://orcid.org/0000-0002-0395-9976"]},"institutions":[{"id":"https://openalex.org/I51209816","display_name":"Eski\u015fehir Osmangazi University","ror":"https://ror.org/01dzjez04","country_code":"TR","type":"education","lineage":["https://openalex.org/I51209816"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Emrah ATILGAN","raw_affiliation_strings":["Eskisehir Osmangazi Universitesi Muhendislik Mimarlik Fakultesi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eskisehir Osmangazi Universitesi Muhendislik Mimarlik Fakultesi","institution_ids":["https://openalex.org/I51209816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064406152","display_name":"Menderes Tarcan","orcid":"https://orcid.org/0000-0003-3989-2440","observed_orcids":["https://orcid.org/0000-0003-3989-2440"]},"institutions":[{"id":"https://openalex.org/I51209816","display_name":"Eski\u015fehir Osmangazi University","ror":"https://ror.org/01dzjez04","country_code":"TR","type":"education","lineage":["https://openalex.org/I51209816"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Menderes Tarcan","raw_affiliation_strings":["Eskisehir Osmangazi Universitesi"],"raw_orcid":"https://orcid.org/0000-0003-3989-2440","affiliations":[{"raw_affiliation_string":"Eskisehir Osmangazi Universitesi","institution_ids":["https://openalex.org/I51209816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126165415","display_name":"Alperen Evci","orcid":"https://orcid.org/0009-0003-8695-5528","observed_orcids":["https://orcid.org/0009-0003-8695-5528"]},"institutions":[{"id":"https://openalex.org/I51209816","display_name":"Eski\u015fehir Osmangazi University","ror":"https://ror.org/01dzjez04","country_code":"TR","type":"education","lineage":["https://openalex.org/I51209816"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Alperen Evci","raw_affiliation_strings":["Eskisehir Osmangazi Universitesi Muhendislik Mimarlik Fakultesi"],"raw_orcid":"https://orcid.org/0009-0003-8695-5528","affiliations":[{"raw_affiliation_string":"Eskisehir Osmangazi Universitesi Muhendislik Mimarlik Fakultesi","institution_ids":["https://openalex.org/I51209816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004861568","display_name":"Ne\u015fet Hikmet","orcid":"https://orcid.org/0000-0002-0777-3132","observed_orcids":["https://orcid.org/0000-0002-0777-3132"]},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neset HIKMET","raw_affiliation_strings":["University of South Carolina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Carolina","institution_ids":["https://openalex.org/I155781252"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064406152"],"corresponding_institution_ids":["https://openalex.org/I51209816"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9990000128746033,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9990000128746033,"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/T11943","display_name":"Pharmacovigilance and Adverse Drug Reactions","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/3005","display_name":"Toxicology"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":9.999999747378752e-05,"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/bert","display_name":"BERT","score":0.7369999885559082},{"id":"https://openalex.org/keywords/post-marketing-surveillance","display_name":"post-marketing surveillance","score":0.8500000238418579},{"id":"https://openalex.org/keywords/diabetes-management","display_name":"diabetes management","score":0.7429999709129333},{"id":"https://openalex.org/keywords/online-consumer-reviews","display_name":"online customer reviews","score":0.9380000233650208},{"id":"https://openalex.org/keywords/infoveillance","display_name":"infoveillance","score":0.7799999713897705},{"id":"https://openalex.org/keywords/real-world-evidence","display_name":"real-world evidence","score":0.7860000133514404},{"id":"https://openalex.org/keywords/medical-device-safety","display_name":"medical device safety","score":0.8320000171661377},{"id":"https://openalex.org/keywords/agglutinative-languages","display_name":"agglutinative languages","score":0.828000009059906}],"concepts":[{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.8342999815940857},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40459999442100525},{"id":"https://openalex.org/C2776217022","wikidata":"https://www.wikidata.org/wiki/Q1100933","display_name":"Diabetes management","level":4,"score":0.39649999141693115},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.38519999384880066},{"id":"https://openalex.org/C555293320","wikidata":"https://www.wikidata.org/wiki/Q12206","display_name":"Diabetes mellitus","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C3019806175","wikidata":"https://www.wikidata.org/wiki/Q11974939","display_name":"Health professionals","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.289000004529953},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.28790000081062317},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.260699987411499}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.22541/au.177123975.54573004/v1","doi":"https://doi.org/10.22541/au.177123975.54573004/v1","is_oa":true,"landing_page_url":"https://doi.org/10.22541/au.177123975.54573004/v1","pdf_url":"https://www.authorea.com/doi/pdf/10.22541/au.177123975.54573004","source":null,"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.22541/au.177123975.54573004/v1","doi":"https://doi.org/10.22541/au.177123975.54573004/v1","is_oa":true,"landing_page_url":"https://doi.org/10.22541/au.177123975.54573004/v1","pdf_url":"https://www.authorea.com/doi/pdf/10.22541/au.177123975.54573004","source":null,"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.9537000060081482}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7129013445.pdf","grobid_xml":"https://content.openalex.org/works/W7129013445.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387460638","https://openalex.org/W3205659225","https://openalex.org/W3206241706","https://openalex.org/W7128697984","https://openalex.org/W4416183743","https://openalex.org/W7130871587","https://openalex.org/W4415115096","https://openalex.org/W4416114356","https://openalex.org/W4416211491","https://openalex.org/W3186181777"],"abstract_inverted_index":{"Background:":[0],"Sentiment":[1],"analysis":[2,60],"in":[3,108,285],"Turkish":[4,63,135,153,164,252],"is":[5],"particularly":[6],"challenging":[7],"due":[8],"to":[9,49,67,71,88,140,185,298],"the":[10,19,90,158,187,209,224,248],"language\u2019s":[11],"agglutinative":[12],"structure":[13],"and":[14,42,66,96,146,169,174,205,219,231,253,271,295,302],"rich":[15],"morphological":[16],"variation.":[17],"At":[18],"same":[20],"time,":[21],"consumer-generated":[22,276],"data":[23,277],"on":[24],"healthcare":[25],"products\u2014especially":[26],"self-monitoring":[27],"blood":[28],"glucose":[29],"(SMBG)":[30],"systems\u2014represent":[31],"an":[32,85],"underutilized":[33],"source":[34,284],"of":[35,128,151,157,189,251,261],"real-world":[36,97],"evidence":[37],"for":[38,62,79,104,163,269],"understanding":[39],"device":[40,130,287],"performance":[41,178],"user":[43,236],"experience.":[44],"Objective:":[45],"This":[46,82],"study":[47,83],"aims":[48],"develop":[50],"a":[51,75,101,281],"Bidirectional":[52],"Encoder":[53],"Representations":[54],"from":[55,258],"Transformers":[56],"(BERT)":[57],"based":[58],"sentiment":[59,165,212,256],"model":[61,103,137,196,225],"e-commerce":[64,154],"reviews":[65,260],"evaluate":[68],"its":[69],"applicability":[70],"SMBG":[72,210,262],"devices":[73],"as":[74,280],"potential":[76,267],"complementary":[77,282],"tool":[78],"post-market":[80,286],"surveillance.":[81,288],"utilizes":[84],"infoveillance":[86,117],"approach":[87],"bridge":[89],"gap":[91],"between":[92],"traditional":[93,182],"vigilance":[94,272],"systems":[95],"patient":[98],"experiences,":[99],"providing":[100,125],"scalable":[102],"digital":[105],"health":[106,121],"surveillance":[107],"non-English":[109],"speaking":[110],"contexts.":[111],"Furthermore,":[112],"we":[113],"demonstrate":[114,241],"how":[115],"this":[116],"framework":[118],"can":[119,245],"support":[120],"policy":[122],"decision-making":[123],"by":[124],"real-time":[126],"oversight":[127],"medical":[129],"safety.":[131],"Methods:":[132],"A":[133,149],"pre-trained":[134],"BERT":[136,195],"was":[138,167,179,214],"fine-tuned":[139,194],"classify":[141],"sentiments":[142],"into":[143,235],"positive,":[144,216],"negative,":[145,218],"neutral":[147],"categories.":[148],"corpus":[150],"75,000":[152],"reviews,":[155],"one":[156],"largest":[159],"manually":[160],"annotated":[161],"datasets":[162],"analysis,":[166],"collected":[168],"processed":[170],"through":[171],"tokenization,":[172],"cleaning,":[173],"manual":[175],"labeling.":[176],"Model":[177],"compared":[180],"with":[181],"machine-learning":[183],"baselines":[184],"assess":[186],"benefits":[188],"contextual":[190],"embeddings.":[191],"Results:":[192],"The":[193,239],"outperformed":[197],"all":[198],"baseline":[199],"classifiers,":[200],"achieving":[201],"higher":[202],"overall":[203],"accuracy":[204],"class-wise":[206],"F1-scores.":[207],"In":[208],"subset,":[211],"distribution":[213],"89.44%":[215],"7.22%":[217],"3.33%":[220],"neutral,":[221],"indicating":[222],"that":[223,242,275],"successfully":[226],"captured":[227],"fine-grained":[228],"linguistic":[229,249],"cues":[230],"provided":[232],"robust":[233],"insights":[234,265],"perspectives.":[237],"Conclusion:":[238],"findings":[240],"BERT-based":[243],"models":[244],"effectively":[246],"address":[247],"complexity":[250],"extract":[254],"meaningful":[255],"patterns":[257],"consumer":[259],"devices.":[263],"These":[264],"show":[266],"value":[268],"regulatory":[270],"contexts,":[273],"suggesting":[274],"could":[278],"serve":[279],"early-signal":[283],"Future":[289],"work":[290],"may":[291],"integrate":[292],"multimodal":[293],"inputs":[294],"explainability":[296],"techniques":[297],"improve":[299],"domain":[300],"adaptability":[301],"transparency.":[303]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-17T00:00:00"}