Learning Relationship between Authorsʹ Activity and Sentiments: A case study of online medical forums

Abstract

Our current work analyses relations between sentiments and activity of authors of online In-Vitro Fertilization forums. We focus on two types of active authors: those who start new discussions and those who post significantly more messages than other authors. By incorporating authors‟ activity information into a domain-specific lexical representation of messages, we were able to improve multi-class classification of sentiments by 9% for Support Vector Machines and by 15.3 % for Conditional Random Fields.