Deep Health Care Text Classification

TL;DR

This paper introduces RNN and LSTM based models for automatic health-related social media text classification, demonstrating their effectiveness without feature engineering on a health social media dataset.

Contribution

It presents a novel application of RNN and LSTM models for health text classification that do not require feature engineering, improving classification accuracy.

Findings

RNN and LSTM models effectively classify health-related tweets.

The proposed methods outperform traditional feature-engineering approaches.

Models are validated on a shared task dataset with significant results.

Abstract

Health related social media mining is a valuable apparatus for the early recognition of the diverse antagonistic medicinal conditions. Mostly, the existing methods are based on machine learning with knowledge-based learning. This working note presents the Recurrent neural network (RNN) and Long short-term memory (LSTM) based embedding for automatic health text classification in the social media mining. For each task, two systems are built and that classify the tweet at the tweet level. RNN and LSTM are used for extracting features and non-linear activation function at the last layer facilitates to distinguish the tweets of different categories. The experiments are conducted on 2nd Social Media Mining for Health Applications Shared Task at AMIA 2017. The experiment results are considerable; however the proposed method is appropriate for the health text classification. This is primarily due to the reason that, it doesn't rely on any feature engineering mechanisms.