Enhancing EmoBot: An In-Depth Analysis of User Satisfaction and Faults in an Emotion-Aware Chatbot

TL;DR

This study delves into an existing state-of-the-art emotional chatbot, EmoBot, designed for generating emotions in general-purpose conversations, including a survey to evaluate its proficiency in key dimensions like usability, accuracy, and overall user satisfaction.

Abstract

The research community has traditionally shown a keen interest in emotion modeling, with a notable emphasis on the detection aspect. In contrast, the exploration of emotion generation has received less attention.This study delves into an existing state-of-the-art emotional chatbot, EmoBot, designed for generating emotions in general-purpose conversations. This research involves a comprehensive examination, including a survey to evaluate EmoBot's proficiency in key dimensions like usability, accuracy, and overall user satisfaction, with a specific focus on fault tolerance. By closely examining the chatbot's operations, we identified some noteworthy shortcomings in the existing model. We propose some solutions designed to address and overcome the identified issues.

Figures (5)

• Figure 1: Implementation steps of the emotion generation system
• Figure 2: Flowchart of the work procedure
• Figure 3: Average ratings on the metrics from the survey
• Figure 4: Emobot fails to recognize "surprise"
• Figure 5: Average ratings on enhanced Emobot from the survey