Emotion Recognition in Text using Graph Similarity Criteria

Emotion recognition is a problem that can be connected to different fields such as natural language processing, computer vision, deep learning, etc.[4] In this paper, the focus is on the task of recognizing emotions in texts. In the literature, several approaches have been introduced that target this problem. Some of them employ vertex embedding vectors for emotion detection and recognition from text. The embedding vectors grasp the information related to semantics and syntax; however, a limitation of such approaches is that they do not capture the emotional relationship that exists between words. Some methods attempting to alleviate this issue include building a neural network architecture adopting pre-trained word representations.[3] Some text classification approaches employ -grams to construct the text representation, eg, to deal with the task of language identification.[9] In this paper, the approach to emotion recognition employs grams to obtain graph representation of text. The text is viewed as a sequence of characters that is divided into -grams, ie, shorter overlapping sequences of characters as presented in Figure 1.