Emotional States Detection Model from Handwriting by using Machine Learning

Abstract

Handwriting analysis is a multi-level approach for detecting emotion. Every person’s handwriting is different, representing how we think, feel, and act at that time. A person’s emotion is expressed in his handwriting, whether happy or sad, excited, angry, or depressed. We transmit our feelings to paper during the writing process and the way we write symbolizes those emotions. Emotion detection is an important area of study in human-computer interaction. Researchers have done a substantial amount of work to detect emotion from visual and auditory data but recognizing emotions from handwritten data is still a new and active study topic. Mostly, studies on emotion recognition focus on only 3 basic emotions: anxiety, stress, and depression. The main objective of this research is to detect the writer’s emotions from his or her handwriting, so to determine the writer’s mental state and identify those who are emotionally disturbed or sad and require mental help to overcome negative feelings and analyze the changes in handwriting patterns in different emotional states.