Automatic Identification of Drugs and Adverse Drug Reaction Related Tweets

AbstractWe describe our submissions to the Third Social Media Mining for Health Applications Shared Task. We participated in two tasks (tasks 1 and 3). For both tasks, we experimented with a traditional machine learning model (Naive Bayes Support Vector Machine (NBSVM)), deep learning models (Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Bidirectional LSTM (BiLSTM)), and the combination of deep learning model with SVM. We observed that the NBSVM reaches superior performance on both tasks on our development split of the training data sets. Official result for task 1 based on the blind evaluation data shows that the predictions of the NBSVM achieved our team’s best F-score of 0.910 which is above the average score received by all submissions to the task. On task 3, the combination of of BiLSTM and SVM gives our best F-score for the positive class of 0.394.