Introduction

Abstract

This introductory chapter offers an updated literature review of sentiment analysis research and explains the importance of common-sense knowledge as a means to better understand natural language. In particular, the chapter proposes insights on the evolution of opinion mining research from heuristics to discourse structure, from coarse- to fine-grained analysis, and from keyword to concept-level polarity detection. Subsequently, a comprehensive literature review on common-sense knowledge representation is proposed, together with a discussion on why common-sense is important for sentiment analysis and natural language understanding. The chapter ends with an introduction of sentic computing as a new common-sense based framework for concept-level sentiment analysis and the explanation of its three key shifts, which highly differentiate it from standard approaches to opinion mining and social media analysis.