What Sentiments Can Be Found in Medical Forums?

Abstract

In this work we present sentiment analysis of messages posted on a medical forum. We categorize posts, written in English, into five categories: encouragement, gratitude, confusion, facts, and facts + sentiments. Our study applies a manual sentiment annotation, affective lexicons in its sentiment analysis and machine learning classification of sentiments in these texts. We report empirical results obtained from analysis of 752 posts dedicated to infertility treatments. Our best results improve multi-class sentiment classification of online messages (F-score = 0.518, AUC=0.685).