Multitask Personalized Recognition of Emotions Evoked by Textual Content

Abstract

In this paper, we present the studies on personalized emotion recognition in text perception in the multitask setting. We analyze the performance of the joint learning of the model within groups of similar tasks (sub-multitask approach) and for all tasks learned together (full multitask) versus the classical approach based on separate models dedicated to each individual task (single-task). Additionally, we use our novel personalized deep learning architectures capable of recognizing emotions from the user’s perspective through the calculated Human Bias and learned vector representation of the user. These methods are combined with state-of-the-art linguistic models based on transformers to represent the textual content. The results show a significant gain in emotion recognition quality in both sub-multitask and multitask scenarios. In each setup, personalization yields a significant quality gain, which is essential from the perspective of AI systems responding to the emotions of a specific user.