Sentiments and Opinions Annotation in User-generated Texts

Abstract

In this work, we analyze sentiments and opinions expressed in user-written Web messages. The messages discuss health related topics: medications, treatment, illness and cure, etc. Recognition of sentiments and opinions is a challenging task for humans as well as an automated text analysis. The paper presents the annotation model, discusses characteristics of subjectivity annotations in health-related messages, and reports the results of the annotation agreement.