Cognitive Based Sentence Level Emotion Estimation through Emotional Expressions

Abstract

The present approach deals with the extraction of emotional patterns in the phrases of sentences. The proposed approach identifies emotional patterns from POS tags of emotion triggered terms and its co-occurrence terms. The sentence patterns are classified hierarchically into 16 classes with positive and negative emotions. Suitable intensities are assigned for capturing the degree of emotion contents that exist in semantics of patterns. Neural network based supervised framework is employed for classifying the sentences into positive and negative emotional sentence patterns. The proposed hierarchical classification approach performs well and achieves good F-Scores. © Springer International Publishing Switzerland 2015.