Adverse drug reaction corpus of tweets

Overview

The vast amount of data on social media presents significant opportunities and challenges for utilizing it as a resource for health informatics. The aim of the Social Media Mining for Health Applications (#SMM4H) shared tasks is to take a community-driven approach to address natural language processing challenges of using social media data for health informatics, including informal, colloquial expressions of clinical concepts, noise, data sparsity, ambiguity, and multilingual posts.

In this talk, Elena Tutubalina and Ilseyar Alimova introduce SMM4H 2020 & 2021 shared tasks and the first Russian adverse drug reaction corpus of tweets. Elena describes three tasks on mining adverse drug effects using annotated datasets, focusing on current challenges and the imbalanced nature of the datasets. Ilseyar describes the creation of the Russian dataset, focusing on the data collection and annotation process. At the end of the talk, the results of participants of the SMM4H shared tasks on the classification of Russian tweets are discussed. This is a joint work with the University of Pennsylvania, USA.

Speakers

Elena Tutubalina

Insilico MedicineElena Tutubalina is a senior research scientist at Insilico Medicine. She has written her Ph.D. thesis at Kazan Federal University and defended it at the Institute for Systems Programming, Russian Academy of Sciences in 2016. Dr. Tutubalina has more than 40 papers in the NLP field, including publications in Q1 journals and on such conferences as COLING, ECIR, WSDM.Profile link

Ilseyar Alimova

Insilico MedicineIlseyar Alimova has written her Ph.D. thesis at Kazan Federal University and is defending it at the Institute for Systems Programming, Russian Academy of Sciences. She has more than 20 papers in the NLP field. Her main research interests are information extraction, representation learning, multilingual models.