Did you take the pill? - Detecting Personal Intake of Medicine from Twitter

TL;DR

This paper presents a CNN ensemble classifier that accurately detects personal medication intake mentions in tweets, enabling individual-level health monitoring and pharmacovigilance from social media data.

Contribution

It introduces a novel stacked CNN ensemble trained on annotated tweets, achieving state-of-the-art performance in identifying personal medicine intake mentions.

Findings

Achieved a micro-averaged F-score of 0.693 on the classification task.

Developed a hyper-parameter tuned ensemble of CNN models.

Demonstrated potential applications in health informatics and pharmacovigilance.

Abstract

Mining social media messages such as tweets, articles, and Facebook posts for health and drug related information has received significant interest in pharmacovigilance research. Social media sites (e.g., Twitter), have been used for monitoring drug abuse, adverse reactions of drug usage and analyzing expression of sentiments related to drugs. Most of these studies are based on aggregated results from a large population rather than specific sets of individuals. In order to conduct studies at an individual level or specific cohorts, identifying posts mentioning intake of medicine by the user is necessary. Towards this objective we develop a classifier for identifying mentions of personal intake of medicine in tweets. We train a stacked ensemble of shallow convolutional neural network (CNN) models on an annotated dataset. We use random search for tuning the hyper-parameters of the CNN models and present an ensemble of best models for the prediction task. Our system produces state-of-the-art result, with a micro-averaged F-score of 0.693. We believe that the developed classifier has direct uses in the areas of psychology, health informatics, pharmacovigilance and affective computing for tracking moods, emotions and sentiments of patients expressing intake of medicine in social media.