User-Centric Design: Adjective Rating Scale for Conversational Agent Interaction

The study focuses on evaluating user experience with Conversational Agents (CA) with the help of a comprehensive adjective rating scale. By developing a nuanced measurement tool, the research aims to capture the user experience of CA. The study carried out a methodological rigor through experiments and structured procedures. The outcome show a positive relationship between adjective and scale scores, highlighting the reliability of adjective rating scale. The research also draw light to the importance of holistic assessment in user experience evaluation and how they are valuable tool for designers and project managers in today's AI climate.