InfyNLP at SMM4H Task 2: Stacked Ensemble of Shallow Convolutional Neural Networks for Identifying Personal Medication Intake from Twitter

TL;DR

This paper presents a stacked ensemble of shallow CNNs for classifying tweets about personal medication intake, achieving top performance in a shared task with an F-score of 0.693.

Contribution

It introduces a novel ensemble approach of shallow CNNs with hyper-parameter tuning for social media health message classification.

Findings

Achieved first place in the shared task competition.

Secured a micro-averaged F-score of 0.693.

Demonstrated effectiveness of shallow CNN ensembles for health-related tweet classification.

Abstract

This paper describes Infosys's participation in the "2nd Social Media Mining for Health Applications Shared Task at AMIA, 2017, Task 2". Mining social media messages for health and drug related information has received significant interest in pharmacovigilance research. This task targets at developing automated classification models for identifying tweets containing descriptions of personal intake of medicines. Towards this objective we train a stacked ensemble of shallow convolutional neural network (CNN) models on an annotated dataset provided by the organizers. We use random search for tuning the hyper-parameters of the CNN and submit an ensemble of best models for the prediction task. Our system secured first place among 9 teams, with a micro-averaged F-score of 0.693.