{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:53:14Z","timestamp":1782845594044,"version":"3.54.5"},"reference-count":21,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Social networking services (SNS) closely reflect the lives of individuals in modern society and generate large amounts of data. Previous studies have extracted drug information using relevant SNS data. In particular, it is important to detect adverse drug reactions (ADRs) early using drug surveillance systems. To this end, various deep learning methods have been used to analyze data in multiple languages in addition to English.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>A cautionary drug that can cause ADRs in older patients was selected, and Korean SNS data containing this drug information were collected. Based on this information, we aimed to develop a deep learning model that classifies drug ADR posts based on a recurrent neural network.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In previous studies, ketoprofen, which has a high prescription frequency and, thus, was referred to the most in posts secured from SNS data, was selected as the target drug. Blog posts, caf\u00e9 posts, and NAVER Q&amp;A posts from 2005 to 2020 were collected from NAVER, a portal site containing drug-related information, and natural language processing techniques were applied to analyze data written in Korean. Posts containing highly relevant drug names and ADR word pairs were filtered through association analysis, and training data were generated through manual labeling tasks. Using the training data, an embedded layer of word2vec was formed, and a Bidirectional Long Short-Term Memory (Bi-LSTM) classification model was generated. Then, we evaluated the area under the curve with other machine learning models. In addition, the entire process was further verified using the nonsteroidal anti-inflammatory drug aceclofenac.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the nonsteroidal anti-inflammatory drugs, Korean SNS posts containing information on ketoprofen and aceclofenac were secured, and the generic name lexicon, ADR lexicon, and Korean stop word lexicon were generated. In addition, to improve the accuracy of the classification model, an embedding layer was created considering the association between the drug name and the ADR word. In the ADR post classification test, ketoprofen and aceclofenac achieved 85% and 80% accuracy, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Here, we propose a process for developing a model for classifying ADR posts using SNS data. After analyzing drug name-ADR patterns, we filtered high-quality data by extracting posts, including known ADR words based on the analysis. Based on these data, we developed a model that classifies ADR posts. This confirmed that a model that can leverage social data to monitor ADRs automatically is feasible.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/45289","type":"journal-article","created":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T06:39:39Z","timestamp":1722926379000},"page":"e45289-e45289","source":"Crossref","is-referenced-by-count":2,"title":["Bidirectional Long Short-Term Memory\u2013Based Detection of Adverse Drug Reaction Posts Using Korean Social Networking Services Data: Deep Learning Approaches"],"prefix":"10.2196","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1670-6222","authenticated-orcid":false,"given":"Chung-Chun","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2273-0915","authenticated-orcid":false,"given":"Seunghee","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7047-8032","authenticated-orcid":false,"given":"Mi-Hwa","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1230-9307","authenticated-orcid":false,"given":"Jong-Yeup","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0651-6481","authenticated-orcid":false,"given":"Suehyun","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"issue":"18","key":"R1","doi-asserted-by":"publisher","first-page":"2268","DOI":"10.1093\/ajhp\/51.18.2268","article-title":"Factors associated with preventable adverse drug reactions","volume":"51","author":"Pearson","journal-title":"Am J Health Syst Pharm"},{"issue":"1_suppl","key":"R2","doi-asserted-by":"publisher","first-page":"S73","DOI":"10.4103\/0976-500X.120957","article-title":"Clinical and economic burden of adverse drug reactions","volume":"4","author":"Sultana","journal-title":"J Pharmacol Pharmacother"},{"issue":"12","key":"R3","doi-asserted-by":"publisher","first-page":"1355","DOI":"10.1007\/s40264-018-0699-2","article-title":"Assessment of the utility of social media for broad-ranging statistical signal detection in pharmacovigilance: results from the WEB-RADR project","volume":"41","author":"Caster","journal-title":"Drug Saf"},{"issue":"4","key":"R4","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1093\/jamia\/ocw180","article-title":"Deep learning for pharmacovigilance: recurrent neural network architectures for labeling adverse drug reactions in Twitter posts","volume":"24","author":"Cocos","journal-title":"J Am Med Inform Assoc"},{"issue":"3","key":"R5","doi-asserted-by":"publisher","first-page":"319","DOI":"10.22074\/cellj.2020.6615","article-title":"Adverse drug reaction detection in social media by deepm learning methods","volume":"22","author":"Rezaei","journal-title":"Cell J"},{"issue":"4","key":"R6","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare10040618","article-title":"Predicting adverse drug reactions from social media posts: data balance, feature selection and deep learning","volume":"10","author":"Huang","journal-title":"Healthcare (Basel) - Healthc (Basel)"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2015.03.010","article-title":"Cadec: a corpus of adverse drug event annotations","volume":"55","author":"Karimi","journal-title":"J Biomed Inform"},{"issue":"4","key":"R8","doi-asserted-by":"publisher","first-page":"848","DOI":"10.1007\/s10618-018-00610-2","article-title":"Automatic discovery of adverse reactions through Chinese social media","volume":"33","author":"Zhang","journal-title":"Data Min Knowl Disc"},{"issue":"2","key":"R9","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1093\/bioinformatics\/btaa675","article-title":"The Russian Drug Reaction Corpus and neural models for drug reactions and effectiveness detection in user reviews","volume":"37","author":"Tutubalina","journal-title":"Bioinformatics"},{"issue":"3","key":"R10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0191376","article-title":"South Korean geriatrics on Beers Criteria medications at risk of adverse drug events","volume":"13","author":"Kim","journal-title":"PLoS One"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2021.104542","article-title":"Geriatrics on beers criteria medications at risk of adverse drug events using real-world data","volume":"154","author":"Shin","journal-title":"Int J Med Inform"},{"issue":"2","key":"R12","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1177\/009286158902300208","article-title":"World Health Organization Adverse Reaction Terminology Dictionary","volume":"23","author":"Sills","journal-title":"Drug Inf J"},{"issue":"D1","key":"R13","doi-asserted-by":"publisher","first-page":"D1075","DOI":"10.1093\/nar\/gkv1075","article-title":"The SIDER database of drugs and side effects","volume":"44","author":"Kuhn","journal-title":"Nucleic Acids Res"},{"key":"R14","unstructured":"Education, public relations. Korea Institute of Drug Safety & Risk Management. 2015. URL: https:\/\/www.drugsafe.or.kr\/iwt\/ds\/ko\/bbs\/EgovBbs.do;jsessionid=JcVbUVsrD2anWzye6BgkPqwiw4cktqW0oiFbNuq2WQaDVhqlgoXgLidzeTEGPuTz.webint_2_servlet_engine1?bbsId=BBSMSTR_000000000024&nttId=1446&pageIndex=2&searchCnd=&searchWrd= [Accessed 14-10-2024]"},{"key":"R15","unstructured":"Lee MC Yang HM Kim GY . bab2min\/Kiwi. GitHub. 2018. URL: https:\/\/github.com\/bab2min\/kiwi [Accessed 14-10-2024]"},{"issue":"4","key":"R16","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/S0306-4379(03)00072-3","article-title":"Selecting the right objective measure for association analysis","volume":"29","author":"Tan","journal-title":"Inf Syst"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.9708\/jksci.2021.26.05.039","article-title":"A text content classification using LSTM for objective category classification","volume":"26","author":"Noh","journal-title":"J Korea Soc Comput Inf"},{"key":"R18","unstructured":"What medicines should senior citizens be careful of?. The Korea Ministry of Food and Drug Safety. 2021. URL: https:\/\/www.mfds.go.kr\/brd\/m_99\/view.do?seq=45568&srchFr=&srchTo=&srchWord=&srchTp=&itm_seq_1=0&itm_seq_2=0&multi_itm_seq=0&company_cd=&company_nm=&page=39 [Accessed 14-10-2024]"},{"issue":"12","key":"R19","doi-asserted-by":"publisher","first-page":"1393","DOI":"10.1007\/s40264-019-00858-7","article-title":"Recommendations for the use of social media in pharmacovigilance: lessons from IMI WEB-RADR","volume":"42","author":"van Stekelenborg","journal-title":"Drug Saf"},{"issue":"9","key":"R20","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1007\/s40264-020-00943-2","article-title":"Combining social media and FDA adverse event reporting system to detect adverse drug reactions","volume":"43","author":"Li","journal-title":"Drug Saf"},{"issue":"10","key":"R21","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.6426","article-title":"Scaling up research on drug abuse and addiction through social media big data","volume":"19","author":"Kim","journal-title":"J Med Internet Res"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2024\/1\/e45289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:50:43Z","timestamp":1782841843000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2024\/1\/e45289"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":21,"URL":"https:\/\/doi.org\/10.2196\/45289","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,20]]},"article-number":"v12i18e45289"}}