Task 2 : Classification of Russian tweets for detecting presence of adverse effect (AE) mentions

The designed system for this subtask should be able to distinguish tweets reporting an adverse effect from those that do not, taking into account subtle linguistic variations between adverse effects and indications (the reason to use the medication).

  • Training data: 11,610 tweets
  • Test data: 1000 tweets

Register your team here : https://forms.gle/1qs3rdNLDxAph88n6
Link to Codalab : Available Feb 1 2021

We thank Yandex.Toloka for supporting the shared task and providing credits for data annotation in Russian.

Evaluation Metric : F1-score for the AE class

Contact information: Elena Tutubalina (tutubalinaev@gmail.com)

We thank Yandex.Toloka for supporting the shared task and providing credits for data annotation in Russian.

References:

SMM4H 2020 proceedings

The Russian Drug Reaction Corpus and Neural Models

We provide two Python tutorials on how to run classifiers on SMMH4 data:
CNN-based classifier on SMM4H Task 2 data (ADR classification)
BERT-based classifier on SMM4H Task 2 data