{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T05:21:12Z","timestamp":1784092872414,"version":"3.55.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"25","license":[{"start":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T00:00:00Z","timestamp":1635465600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T00:00:00Z","timestamp":1635465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["3P30AG059307-02S1"],"award-info":[{"award-number":["3P30AG059307-02S1"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s00521-021-06614-2","type":"journal-article","created":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T10:03:06Z","timestamp":1635501786000},"page":"18161-18169","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Using weak supervision to generate training datasets from social media data: a proof of concept to identify drug mentions"],"prefix":"10.1007","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1606-4856","authenticated-orcid":false,"given":"Ramya","family":"Tekumalla","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8499-824X","authenticated-orcid":false,"given":"Juan M.","family":"Banda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,10,29]]},"reference":[{"key":"6614_CR1","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1016\/j.jbi.2015.02.004","volume":"54","author":"A Sarker","year":"2015","unstructured":"Sarker A, Ginn R, Nikfarjam A et al (2015) Utilizing social media data for pharmacovigilance: A review. J Biomed Inform 54:202\u2013212. https:\/\/doi.org\/10.1016\/j.jbi.2015.02.004","journal-title":"J Biomed Inform"},{"key":"6614_CR2","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1093\/nsr\/nwx106","volume":"5","author":"Z-H Zhou","year":"2017","unstructured":"Zhou Z-H (2017) A brief introduction to weakly supervised learning. Natl Sci Rev 5:44\u201353. https:\/\/doi.org\/10.1093\/nsr\/nwx106","journal-title":"Natl Sci Rev"},{"key":"6614_CR3","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv [cs.CL]"},{"key":"6614_CR4","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1093\/jamia\/ocw180","volume":"24","author":"A Cocos","year":"2017","unstructured":"Cocos A, Fiks AG, Masino AJ (2017) Deep learning for pharmacovigilance: recurrent neural network architectures for labeling adverse drug reactions in Twitter posts. J Am Med Inform Assoc 24:813\u2013821. https:\/\/doi.org\/10.1093\/jamia\/ocw180","journal-title":"J Am Med Inform Assoc"},{"key":"6614_CR5","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1093\/jamia\/ocu041","volume":"22","author":"A Nikfarjam","year":"2015","unstructured":"Nikfarjam A, Sarker A, O\u2019Connor K et al (2015) Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features. J Am Med Inform Assoc 22:671\u2013681. https:\/\/doi.org\/10.1093\/jamia\/ocu041","journal-title":"J Am Med Inform Assoc"},{"key":"6614_CR6","unstructured":"Ratner A, Varma P, Hancock B, et al (2019) Weak Supervision: A New Programming Paradigm for Machine Learning. http:\/\/ai.stanford.edu\/blog\/weak-supervision\/. Accessed 23 Nov 2020"},{"key":"6614_CR7","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/BF00116829","volume":"2","author":"D Angluin","year":"1988","unstructured":"Angluin D, Laird P (1988) Learning from noisy examples. Mach Learn 2:343\u2013370. https:\/\/doi.org\/10.1007\/BF00116829","journal-title":"Mach Learn"},{"key":"6614_CR8","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1162\/neco.1995.7.1.108","volume":"7","author":"CM Bishop","year":"1995","unstructured":"Bishop CM (1995) Training with noise is equivalent to Tikhonov regularization. Neural Comput 7:108\u2013116. https:\/\/doi.org\/10.1162\/neco.1995.7.1.108","journal-title":"Neural Comput"},{"key":"6614_CR9","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1006\/jcss.1996.0019","volume":"52","author":"HU Simon","year":"1996","unstructured":"Simon HU (1996) General bounds on the number of examples needed for learning probabilistic concepts. J Comput System Sci 52:239\u2013254. https:\/\/doi.org\/10.1006\/jcss.1996.0019","journal-title":"J Comput System Sci"},{"key":"6614_CR10","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/0020-0190(96)00006-3","volume":"57","author":"JA Aslam","year":"1996","unstructured":"Aslam JA, Decatur SE (1996) On the sample complexity of noise-tolerant learning. Inf Process Lett 57:189\u2013195. https:\/\/doi.org\/10.1016\/0020-0190(96)00006-3","journal-title":"Inf Process Lett"},{"key":"6614_CR11","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1093\/jamia\/ocw028","volume":"23","author":"V Agarwal","year":"2016","unstructured":"Agarwal V, Podchiyska T, Banda JM et al (2016) Learning statistical models of phenotypes using noisy labeled training data. J Am Med Inform Assoc 23:1166\u20131173. https:\/\/doi.org\/10.1093\/jamia\/ocw028","journal-title":"J Am Med Inform Assoc"},{"key":"6614_CR12","doi-asserted-by":"publisher","first-page":"825","DOI":"10.2165\/00002018-200730100-00001","volume":"30","author":"M Lindquist","year":"2007","unstructured":"Lindquist M (2007) The need for definitions in pharmacovigilance. Drug Saf 30:825\u2013830. https:\/\/doi.org\/10.2165\/00002018-200730100-00001","journal-title":"Drug Saf"},{"key":"6614_CR13","first-page":"924","volume":"2014","author":"K O\u2019Connor","year":"2014","unstructured":"O\u2019Connor K, Pimpalkhute P, Nikfarjam A et al (2014) Pharmacovigilance on twitter? Mining tweets for adverse drug reactions. AMIA Annu Symp Proc 2014:924\u2013933","journal-title":"AMIA Annu Symp Proc"},{"key":"6614_CR14","unstructured":"Pain J, Levacher J, Quinquenel A, Belz A (2016) Analysis of Twitter data for postmarketing surveillance in pharmacovigilance. In: Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT). pp 94\u2013101"},{"key":"6614_CR15","doi-asserted-by":"publisher","unstructured":"Tekumalla R, Banda JM (2020) Characterizing drug mentions in COVID-19 Twitter Chatter. In: Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020. Association for Computational Linguistics, Online, 2020. https:\/\/doi.org\/10.18653\/v1\/2020.nlpcovid19-2.25","DOI":"10.18653\/v1\/2020.nlpcovid19-2.25"},{"key":"6614_CR16","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1016\/j.dib.2016.11.056","volume":"10","author":"A Sarker","year":"2017","unstructured":"Sarker A, Gonzalez G (2017) A corpus for mining drug-related knowledge from Twitter chatter: Language models and their utilities. Data Brief 10:122\u2013131. https:\/\/doi.org\/10.1016\/j.dib.2016.11.056","journal-title":"Data Brief"},{"key":"6614_CR17","doi-asserted-by":"crossref","unstructured":"Tekumalla R, Asl JR, Banda JM (2020) Mining Archive. org\u2019s Twitter Stream Grab for Pharmacovigilance Research Gold. In: Proceedings of the International AAAI Conference on Web and Social Media. pp 909\u2013917","DOI":"10.1609\/icwsm.v14i1.7357"},{"key":"6614_CR18","doi-asserted-by":"publisher","DOI":"10.5808\/GI.2020.18.2.e16","volume":"18","author":"R Tekumalla","year":"2020","unstructured":"Tekumalla R, Banda JM (2020) Social Media Mining Toolkit (SMMT). Genomics Inform 18:e16. https:\/\/doi.org\/10.5808\/GI.2020.18.2.e16","journal-title":"Genomics Inform"},{"key":"6614_CR19","unstructured":"Machine W (2015) The Internet Archive. Searched for https:\/\/www.icannorg\/icp\/icp-1html"},{"key":"6614_CR20","first-page":"136","volume":"2017","author":"A Klein","year":"2017","unstructured":"Klein A, Sarker A, Rouhizadeh M et al (2017) Detecting personal medication intake in Twitter: an annotated corpus and baseline classification system. BioNLP 2017:136\u2013142","journal-title":"BioNLP"},{"key":"6614_CR21","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: Machine Learning in Python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"6614_CR22","doi-asserted-by":"crossref","unstructured":"Zhu Y, Kiros R, Zemel R, et al (2015) Aligning books and movies: Towards story-like visual explanations by watching movies and reading books. In: Proceedings of the IEEE international conference on computer vision. pp 19\u201327","DOI":"10.1109\/ICCV.2015.11"},{"key":"6614_CR23","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee J, Yoon W, Kim S et al (2020) BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36:1234\u20131240. https:\/\/doi.org\/10.1093\/bioinformatics\/btz682","journal-title":"Bioinformatics"},{"key":"6614_CR24","unstructured":"Liu Y, Ott M, Goyal N, et al (2019) RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv [cs.CL]"},{"key":"6614_CR25","unstructured":"Rajapakse T (2020) Simple Transformers Available at https:\/\/github.com\/ThilinaRajapakse\/simpletransformers"},{"key":"6614_CR26","doi-asserted-by":"crossref","unstructured":"Wolf T, Debut L, Sanh V, et al (2019) HuggingFace\u2019s Transformers: State-of-the-art Natural Language Processing. arXiv e-prints. arXiv:1910.03771","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"6614_CR27","unstructured":"Hu B, Lu Z, Li H, Chen Q (2014) Convolutional Neural Network Architectures for Matching Natural Language Sentences. In: Ghahramani Z, Welling M, Cortes C, et al (eds) Advances in Neural Information Processing Systems 27. Curran Associates, Inc., pp 2042\u20132050"},{"key":"6614_CR28","unstructured":"Dos Santos C, Gatti M (2014) Deep convolutional neural networks for sentiment analysis of short texts. In: Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers. pp 69\u201378"},{"key":"6614_CR29","doi-asserted-by":"crossref","unstructured":"Wang P, Xu J, Xu B, et al (2015) Semantic clustering and convolutional neural network for short text categorization. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). pp 352\u2013357","DOI":"10.3115\/v1\/P15-2058"},{"key":"6614_CR30","doi-asserted-by":"publisher","first-page":"150","DOI":"10.3390\/info10040150","volume":"10","author":"K Kowsari","year":"2019","unstructured":"Kowsari K, Jafari Meimandi K, Heidarysafa M et al (2019) Text Classification Algorithms: A Survey. Information 10:150. https:\/\/doi.org\/10.3390\/info10040150","journal-title":"Information"},{"key":"6614_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103307","volume":"99","author":"A Lavertu","year":"2019","unstructured":"Lavertu A, Altman RB (2019) RedMed: Extending drug lexicons for social media applications. J Biomed Inform 99:103307. https:\/\/doi.org\/10.1016\/j.jbi.2019.103307","journal-title":"J Biomed Inform"},{"key":"6614_CR32","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735\u20131780. https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput"},{"key":"6614_CR33","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: Global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"6614_CR34","unstructured":"Godin F (2019) Improving and Interpreting Neural Networks for Word-Level Prediction Tasks in Natural Language Processing. PhD thesis, PhD Thesis, Ghent University, Belgium, 2019. 35"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06614-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06614-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06614-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T23:12:39Z","timestamp":1744153959000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06614-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,29]]},"references-count":34,"journal-issue":{"issue":"25","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["6614"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06614-2","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,29]]},"assertion":[{"value":"3 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}