Emotion Recognition from Text Stories Using an Emotion Embedding model

Abstract

In this paper, we analyze emotions in a story text using an emotion embedding model. Firstly, we collected 144,701 tweets, and each tweet is given an emotional hashtag. Using the emotion hashtag as an emotion label, we built a CNN model for emotion classification. We then extracted the embedding model created during the learning process. We then extracted word embedding layer created during the emotion classification learning process. We defined this as an ‘Emotion embedding model’, and applied it to classify story text emotions. The story text used in emotion analysis was ROC story data, and those story sentences are classified into eight emotions based on plutchik’s emotion model.