E3VA: Enhancing Emotional Expressiveness in Virtual Conversational Agents

TL;DR

This paper introduces E3VA, a virtual conversational agent enhanced with emotional expressiveness using sentiment analysis, aiming to improve user engagement and conversation quality in AI-driven interactions.

Contribution

It presents a novel approach to integrating emotional expressiveness into conversational agents through sentiment analysis and NLP, expanding beyond limited existing contexts.

Findings

Improved user engagement in pilot study

Enhanced emotional responsiveness of the agent

Positive user feedback on conversational quality

Abstract

With the advent of generative AI and large language models, embodied conversational agents are becoming synonymous with online interactions. These agents possess vast amounts of knowledge but suffer from exhibiting limited emotional expressiveness. Without adequate expressions, agents might fail to adapt to users' emotions, which may result in a sub-optimal user experience and engagement. Most current systems prioritize content based responses, neglecting the emotional context of conversations. Research in this space is currently limited to specific contexts, like mental health. To bridge this gap, our project proposes the implementation of expressive features in a virtual conversational agent which will utilize sentiment analysis and natural language processing to inform the generation of empathetic, expressive responses. The project delivers a functional conversational agent capable of assessing and responding to user emotions accordingly. We posit this will enhance usability, engagement, and the overall quality of conversations and present results from an exploratory pilot study investigating the same.