Uncovering Social Media Users’ Emotions Towards Companies Using Semantic Web Technologies

Abstract

In the last few years, online social media networks have witnessed an amazing growth in their worldwide usage, with millions of users constantly publishing messages containing opinions on virtually any imaginable topic, including opinions about companies. Accurately understanding these opinions could provide an almost real-time overview of how the company and its actions are perceived by the general public. While existing approaches used for analyzing the opinions expressed in social media messages commonly limit themselves in discovering the polarity of the messages, expressed as a positive, negative, or neutral value, in the present paper, we use semantic web technologies and natural language processing in order to uncover actual feelings, such as happiness, surprise, or disappointment. The emotions are structured in a hierarchy using an ontology, thus offering the possibility to analyze the overall opinion regarding the company at different levels of granularity. The proposed approach is validated by performing an analysis of the public perception towards four well-known technology companies.