Sentiment-Aware Recommendation System for Healthcare using Social Media
This work addresses the challenge for healthcare users in efficiently finding relevant medical information from large, informal online forums, though it appears incremental as it combines existing deep learning techniques with probabilistic modeling.
The paper tackles the problem of extracting structured medical suggestions from unstructured social media posts by developing a sentiment-aware recommendation system, achieving this through a stacked deep learning model for sentiment analysis and a probabilistic model for treatment suggestions.
Over the last decade, health communities (known as forums) have evolved into platforms where more and more users share their medical experiences, thereby seeking guidance and interacting with people of the community. The shared content, though informal and unstructured in nature, contains valuable medical and/or health-related information and can be leveraged to produce structured suggestions to the common people. In this paper, at first we propose a stacked deep learning model for sentiment analysis from the medical forum data. The stacked model comprises of Convolutional Neural Network (CNN) followed by a Long Short Term Memory (LSTM) and then by another CNN. For a blog classified with positive sentiment, we retrieve the top-n similar posts. Thereafter, we develop a probabilistic model for suggesting the suitable treatments or procedures for a particular disease or health condition. We believe that integration of medical sentiment and suggestion would be beneficial to the users for finding the relevant contents regarding medications and medical conditions, without having to manually stroll through a large amount of unstructured contents.