Building a Concept-Level Sentiment Dictionary Based on Commonsense Knowledge
Angela Charng-Rurng Tsai, Chien Wu, Richard Tzong‐Han Tsai, Jane Yung-jen Hsu · IEEE Intelligent Systems · 2013
Sentiment dictionaries are essential for research in the sentiment analysis field. A two-step method integrates iterative regression and random walk with in-link normalization to build a concept-level sentiment dictionary. The approach uses ConceptNet as a framework to propagate sentiment values, based on the assumption that semantically related concepts share a common sentiment.