Modelling dyads of emotions via sentiment analysis

Abstract

This article presents a new methodology to quantify the probability and magnitude of combinations of emotions -called dyads- through a sentiment analysis which provides prior probabilities of the basic emotions, needed to show the presence of dyads in profiles of people. We classify these features -probability and magnitude- of the dyads into six groups (max, highest, high, medium, low, lowest) in order to identify dyads that have more impact in what we call in this work: positive, negative, neutral, and combined profiles. Positive profiles present mainly Love, while negative profiles present Contempt and Regret. In general, the magnitude of the primary dyads is greater than their probability, not so with the secondary and tertiary dyads where their probability is greater than their magnitude.