Concept-Level Sentiment Analysis with SenticNet

Abstract

SenticNet is a publicly available resource for opinion mining that exploits AI, linguistics, and psychology to infer the polarity associated with commonsense concepts and encode this in a semantic-aware representation. In particular, SenticNet uses dimensionality reduction to calculate the affective valence of multi-word expressions and, hence, represent it in a machine-accessible and machine-processable format. This chapter presents an overview of the most recent sentic computing tools and techniques, with particular focus on applications in the context of big social data analysis.