Task
This is a binary classification task that requires determining whether a tweet contains a mention of an adverse drug reaction (ADR) to a medication (labeled as "1") or not (labeled as "0").
Dataset
The train portion of the dataset consists of 9,515 tweets related to health conditions. These tweets have been labeled based on whether they mention an adverse side effect associated with medication. The dataset was created as part of the Social Media Mining for Health Applications (#SMM4H) Shared Tasks — a track focused on automatically extracting information about drug side effects from tweets. The dataset was prepared in collaboration with the UPenn HLP Center and the Laboratory of Chemoinformatics and Molecular Modeling (KFU). The dataset is publicly available on the Yandex Toloka website (https://toloka.ai/ru/datasets). The test portion of the dataset contains 1,504 tweets and was specifically annotated for this competition.