{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T22:48:30Z","timestamp":1761518910962,"version":"build-2065373602"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Biomedical Informatics"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1016\/j.jbi.2020.103568","type":"journal-article","created":{"date-parts":[[2020,9,14]],"date-time":"2020-09-14T11:29:52Z","timestamp":1600082992000},"page":"103568","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":10,"special_numbering":"C","title":["Learning structured medical information from social media"],"prefix":"10.1016","volume":"110","author":[{"given":"Abul","family":"Hasan","sequence":"first","affiliation":[]},{"given":"Mark","family":"Levene","sequence":"additional","affiliation":[]},{"given":"David","family":"Weston","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"year":"2018","series-title":"MedHelp","key":"10.1016\/j.jbi.2020.103568_b1"},{"key":"10.1016\/j.jbi.2020.103568_b2","doi-asserted-by":"crossref","unstructured":"M.J. Paul, M. Dredze, You are what you tweet: Analyzing twitter for public health, in: Fifth International AAAI Conference on Weblogs and Social Media, July 2011, pp. 265\u2013272.","DOI":"10.1609\/icwsm.v5i1.14137"},{"key":"10.1016\/j.jbi.2020.103568_b3","series-title":"Proceedings of the 2010 Workshop on Biomedical Natural Language Processing","first-page":"117","article-title":"Towards internet-age pharmacovigilance: extracting adverse drug reactions from user posts to health-related social networks","author":"Leaman","year":"2010"},{"key":"10.1016\/j.jbi.2020.103568_b4","doi-asserted-by":"crossref","unstructured":"D. Weissenbacher, A. Sarker, A. Magge, A. Daughton, K. O\u2019Connor, M. Paul, G. Gonzalez, Overview of the fourth social media mining for health (SMM4H) shared tasks at ACL 2019, in: Proceedings of the Fourth Social Media Mining for Health Applications (# SMM4H) Workshop & Shared Task, Aug 2019, pp. 21\u201330.","DOI":"10.18653\/v1\/W19-3203"},{"issue":"9237","key":"10.1016\/j.jbi.2020.103568_b5","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1016\/S0140-6736(00)02799-9","article-title":"Adverse drug reactions: definitions, diagnosis, and management","volume":"356","author":"Edwards","year":"2000","journal-title":"Lancet"},{"key":"10.1016\/j.jbi.2020.103568_b6","series-title":"International Symposium on Intelligent Data Analysis","first-page":"125","article-title":"Natural language analysis of online health forums","author":"Hasan","year":"2017"},{"issue":"1","key":"10.1016\/j.jbi.2020.103568_b7","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1093\/nar\/gkh061","article-title":"The unified medical language system (UMLS): integrating biomedical terminology","volume":"32","author":"Bodenreider","year":"2004","journal-title":"Nucleic Acids Res."},{"issue":"3","key":"10.1016\/j.jbi.2020.103568_b8","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1093\/jamia\/ocu041","article-title":"Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features","volume":"22","author":"Nikfarjam","year":"2015","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jbi.2020.103568_b9","series-title":"Pacific Symposium of Biocomputing (PSB), Vol. 2020","article-title":"Towards identifying drug side effects from social media using active learning and crowd sourcing","author":"Burkhardt","year":"2020"},{"issue":"4","key":"10.1016\/j.jbi.2020.103568_b10","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1561\/2200000013","article-title":"An introduction to conditional random fields","volume":"4","author":"Sutton","year":"2012","journal-title":"Found. Trends Mach. Learn."},{"key":"10.1016\/j.jbi.2020.103568_b11","unstructured":"Z. Miftahutdinov, E. Tutubalina, A. Tropsha, Identifying disease-related expressions in reviews using conditional random fields, in: Proceedings of International Conference on Computational Linguistics and Intellectual Technologies Dialog, Vol. 1, No. 16, Jun 2017, pp. 155\u2013166."},{"key":"10.1016\/j.jbi.2020.103568_b12","series-title":"Introduction to Semi-Supervised Learning","first-page":"1","volume":"vol. 3, no. 1","author":"Zhu","year":"2009"},{"key":"10.1016\/j.jbi.2020.103568_b13","first-page":"1","article-title":"A survey on semi-supervised learning","author":"van Engelen","year":"2019","journal-title":"Mach. Learn."},{"key":"10.1016\/j.jbi.2020.103568_b14","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, in: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun 2019, pp. 4171\u20134186."},{"key":"10.1016\/j.jbi.2020.103568_b15","series-title":"AMIA Annual Symposium Proceedings, Vol. 2008","first-page":"820","article-title":"Unsupervised method for automatic construction of a disease dictionary from a large free text collection","author":"Xu","year":"2008"},{"issue":"2","key":"10.1016\/j.jbi.2020.103568_b16","doi-asserted-by":"crossref","DOI":"10.2196\/12704","article-title":"Development of a consumer health vocabulary by mining health forum texts based on word embedding: Semiautomatic approach","volume":"7","author":"Gu","year":"2019","journal-title":"JMIR Med. Inform."},{"issue":"5","key":"10.1016\/j.jbi.2020.103568_b17","doi-asserted-by":"crossref","first-page":"902","DOI":"10.1136\/amiajnl-2014-002669","article-title":"Induced lexico-syntactic patterns improve information extraction from online medical forums","volume":"21","author":"Gupta","year":"2014","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"1","key":"10.1016\/j.jbi.2020.103568_b18","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/1472-6947-14-91","article-title":"Mining adverse drug reactions from online healthcare forums using hidden markov model","volume":"14","author":"Sampathkumar","year":"2014","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"10.1016\/j.jbi.2020.103568_b19","unstructured":"T. Huynh, Y. He, A. Willis, S. R\u00fcger, Adverse drug reaction classification with deep neural networks, in: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, Dec 2016, pp. 877\u2013887."},{"key":"10.1016\/j.jbi.2020.103568_b20","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.jbi.2015.03.010","article-title":"Cadec: A corpus of adverse drug event annotations","volume":"55","author":"Karimi","year":"2015","journal-title":"J. Biomed. Inform. X"},{"year":"2019","series-title":"AskAPatient","key":"10.1016\/j.jbi.2020.103568_b21"},{"key":"10.1016\/j.jbi.2020.103568_b22","series-title":"Advances in Neural Information Processing Systems","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"Mikolov","year":"2013"},{"issue":"2","key":"10.1016\/j.jbi.2020.103568_b23","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1093\/jamia\/ocv069","article-title":"Active learning: a step towards automating medical concept extraction","volume":"23","author":"Kholghi","year":"2015","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jbi.2020.103568_b24","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1007\/978-3-319-98779-8_17","article-title":"Advancing clinical research through natural language processing on electronic health records: traditional machine learning meets deep learning","author":"Liu","year":"2019","journal-title":"Clin. Res. Inform."},{"issue":"e2","key":"10.1016\/j.jbi.2020.103568_b25","doi-asserted-by":"crossref","first-page":"e253","DOI":"10.1136\/amiajnl-2013-001945","article-title":"Applying active learning to high-throughput phenotyping algorithms for electronic health records data","volume":"20","author":"Chen","year":"2013","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"4","key":"10.1016\/j.jbi.2020.103568_b26","doi-asserted-by":"crossref","DOI":"10.2196\/medinform.9965","article-title":"Clinical named entity recognition from Chinese electronic health records via machine learning methods","volume":"6","author":"Zhang","year":"2018","journal-title":"JMIR Med. Inform."},{"issue":"7","key":"10.1016\/j.jbi.2020.103568_b27","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0210689","article-title":"Twitter mining using semi-supervised classification for relevance filtering in syndromic surveillance","volume":"14","author":"Edo-Osagie","year":"2019","journal-title":"PLoS One"},{"key":"10.1016\/j.jbi.2020.103568_b28","doi-asserted-by":"crossref","unstructured":"K. Lee, A. Qadir, S.A. Hasan, V. Datla, A. Prakash, J. Liu, O. Farri, Adverse drug event detection in tweets with semi-supervised convolutional neural networks, in: Proceedings of the 26th International Conference on World Wide Web, 2017, pp. 705\u2013714.","DOI":"10.1145\/3038912.3052671"},{"issue":"4","key":"10.1016\/j.jbi.2020.103568_b29","first-page":"467","article-title":"Class-based n-gram models of natural language","volume":"18","author":"Brown","year":"1992","journal-title":"Comput. Linguist."},{"key":"10.1016\/j.jbi.2020.103568_b30","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.jbi.2017.05.009","article-title":"Semi-supervised medical entity recognition: A study on Spanish and Swedish clinical corpora","volume":"71","author":"Perez","year":"2017","journal-title":"J. Biomed. Inform."},{"issue":"11","key":"10.1016\/j.jbi.2020.103568_b31","doi-asserted-by":"crossref","first-page":"1529","DOI":"10.1109\/TKDE.2005.186","article-title":"Tri-training: Exploiting unlabeled data using three classifiers","author":"Zhou","year":"2005","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.jbi.2020.103568_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2019.103252","article-title":"Named entity recognition from chinese adverse drug event reports with lexical feature based BiLSTM-CRF and tri-training","volume":"96","author":"Chen","year":"2019","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.jbi.2020.103568_b33","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.jbi.2016.06.007","article-title":"Analysis of the effect of sentiment analysis on extracting adverse drug reactions from tweets and forum posts","volume":"62","author":"Korkontzelos","year":"2016","journal-title":"J. Biomed. Inform. X"},{"key":"10.1016\/j.jbi.2020.103568_b34","doi-asserted-by":"crossref","unstructured":"H. Alhuzali, S. Ananiadou, Improving classification of adverse drug reactions through using sentiment analysis and transfer learning, in: Proceedings of the 18th BioNLP Workshop and Shared Task, Aug 2019, pp. 339\u2013347.","DOI":"10.18653\/v1\/W19-5036"},{"key":"10.1016\/j.jbi.2020.103568_b35","doi-asserted-by":"crossref","unstructured":"C. Wu, F. Wu, J. Liu, S. Wu, Y. Huang, X. Xie, Detecting tweets mentioning drug name and adverse drug reaction with hierarchical tweet representation and multi-head self-attention, in: Proceedings of the 2018 EMNLP Workshop SMM4H: The 3rd Social Media Mining for Health Applications Workshop and Shared Task, Oct 2018, pp. 34\u201337.","DOI":"10.18653\/v1\/W18-5909"},{"issue":"4","key":"10.1016\/j.jbi.2020.103568_b36","first-page":"1234","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"10.1016\/j.jbi.2020.103568_b37","doi-asserted-by":"crossref","unstructured":"E. Alsentzer, J. Murphy, W. Boag, W.-H. Weng, D. Jindi, T. Naumann, M. McDermott, Publicly Available Clinical BERT Embeddings, in: Proceedings of the 2nd Clinical Natural Language Processing Workshop, 2019, pp. 72\u201378.","DOI":"10.18653\/v1\/W19-1909"},{"key":"10.1016\/j.jbi.2020.103568_b38","doi-asserted-by":"crossref","unstructured":"Z. Miftahutdinov, I. Alimova, E. Tutubalina, KFU NLP Team at SMM4H 2019 Tasks: Want to Extract Adverse Drugs Reactions from Tweets? BERT to The Rescue, in: Proceedings of the Fourth Social Media Mining for Health Applications (# SMM4H) Workshop & Shared Task, 2019, pp. 52\u201357.","DOI":"10.18653\/v1\/W19-3207"},{"key":"10.1016\/j.jbi.2020.103568_b39","series-title":"Data Mining: Practical Machine Learning Tools and Techniques","first-page":"163","author":"Witten","year":"2016"},{"year":"2011","series-title":"Text Processing with Gate","author":"Cunningham","key":"10.1016\/j.jbi.2020.103568_b40"},{"key":"10.1016\/j.jbi.2020.103568_b41","series-title":"Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing","first-page":"347","article-title":"Recognizing contextual polarity in phrase-level sentiment analysis","author":"Wilson","year":"2005"},{"year":"2019","series-title":"RXNORM","key":"10.1016\/j.jbi.2020.103568_b42"},{"issue":"1","key":"10.1016\/j.jbi.2020.103568_b43","first-page":"1075","article-title":"The SIDER database of drugs and side effects","volume":"44","author":"Kuhn","year":"2015","journal-title":"Nucleic Acids Res."},{"year":"2018","series-title":"python-crfsuite","key":"10.1016\/j.jbi.2020.103568_b44"},{"year":"2007","series-title":"Crfsuite: a fast implementation of Conditional Random Fields (CRFs)","author":"Okazaki","key":"10.1016\/j.jbi.2020.103568_b45"},{"issue":"151","key":"10.1016\/j.jbi.2020.103568_b46","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1090\/S0025-5718-1980-0572855-7","article-title":"Updating quasi-Newton matrices with limited storage","volume":"35","author":"Nocedal","year":"1980","journal-title":"Math. Comput."},{"issue":"3","key":"10.1016\/j.jbi.2020.103568_b47","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1080\/09296174.2013.799918","article-title":"Binomial confidence intervals and contingency tests: mathematical fundamentals and the evaluation of alternative methods","volume":"20","author":"Wallis","year":"2013","journal-title":"J. Quant. Linguist."},{"issue":"2","key":"10.1016\/j.jbi.2020.103568_b48","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","article-title":"A tutorial on hidden Markov models and selected applications in speech recognition","volume":"77","author":"Rabiner","year":"1989","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.jbi.2020.103568_b49","doi-asserted-by":"crossref","unstructured":"K. Clark, M.-T. Luong, C.D. Manning, Q.V. Le, Semi-supervised sequence modeling with cross-view training, in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018, pp. 1918\u20131925.","DOI":"10.18653\/v1\/D18-1217"},{"key":"10.1016\/j.jbi.2020.103568_b50","unstructured":"G. Vanwinckelen, H. Blockeel, On estimating model accuracy with repeated cross-validation, in: Proceedings of the 21st Belgian-Dutch Conference on Machine Learning, 2012, pp. 39\u201344."},{"issue":"2\u20134","key":"10.1016\/j.jbi.2020.103568_b51","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1002\/cpe.938","article-title":"Distributed computing in practice: the Condor experience","volume":"17","author":"Thain","year":"2005","journal-title":"Concurrency Comput. Pract. Exp."},{"key":"10.1016\/j.jbi.2020.103568_b52","series-title":"Nonparametric Statistical Inference","first-page":"537","author":"Gibbons","year":"2011"}],"container-title":["Journal of Biomedical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046420301982?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1532046420301982?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T22:43:10Z","timestamp":1761518590000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1532046420301982"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":52,"alternative-id":["S1532046420301982"],"URL":"https:\/\/doi.org\/10.1016\/j.jbi.2020.103568","relation":{},"ISSN":["1532-0464"],"issn-type":[{"type":"print","value":"1532-0464"}],"subject":[],"published":{"date-parts":[[2020,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Learning structured medical information from social media","name":"articletitle","label":"Article Title"},{"value":"Journal of Biomedical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jbi.2020.103568","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"Crown Copyright \u00a9 2020 Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"103568"}}