Linguistic Interpretation of Emotions for Affect Sensing from Text

Several approaches have already been employed to “sense” affective information from text, but none of those ever considered the cognitive and appraisal structure of individual emotions. Hence this paper aims at interpreting the cognitive theory of emotions known as the OCC emotion model, from a linguistic standpoint. The paper provides rules for the OCC emotion types for the task of sensing affective information from text. Since the OCC emotions are associated with several cognitive variables, we explain how the values could be assigned to those by analyzing and processing natural language components. Empirical results indicate that our system outperforms another state-of-the-art system.