This study investigates the key factors influencing user satisfaction in human–artificial intelligence interaction (HAI) with chatbots. Using the Cuban Culture Knowledge (CCK) chatbot as a case study, the research aims to examine how emotional state, user experience, task characteristics, service satisfaction, knowledge dissemination efficiency, time and fatigue affect HAI satisfaction.
A controlled experiment was conducted in which participants interacted with the CCK chatbot to complete knowledge-related tasks. The study combined subjective questionnaires with objective eye-tracking measurements to capture user perceptions and interaction behavior. Correlation and regression analyses were applied to examine the relationships between the proposed factors and HAI satisfaction. Given the relatively small sample size, this study adopts an exploratory approach to identify preliminary patterns and relationships among key variables.
The analysis identified six significant predictors of HAI satisfaction: emotional state, user experience, knowledge dissemination efficiency, fixation duration, time, and fatigue. These findings highlight the multidimensional nature of satisfaction with the CCK chatbot.
The findings offer practical insights for improving the design and user experience of AI chatbot systems, particularly by identifying specific features that enhance user satisfaction based on both subjective evaluations and physiological responses measured through eye-tracking data.
