Artificial Intelligence (AI)-driven chatbots have become integral to digital communication, streamlining interactions across customer service, healthcare, and e-commerce. Despite their widespread adoption and advancements in natural language processing (NLP), chatbot interactions are often challenged by misinformation, which can lead to user frustration, dissatisfaction, and disengagement. While prior research has examined user experience (UX) factors such as usability and dialogue quality, limited attention has been given to the specific impact of misinformation on user frustration in AI-driven conversations. This study investigates how misinformation affects user trust and emotional response, exploring the mechanisms that contribute to negative user experiences. Through an empirical evaluation of chatbot interactions, we analyze user reactions to misleading information and assess the effectiveness of potential strategies, such as fact-checking. The findings highlight the need for user-centered chatbot design that prioritizes accuracy and transparency to sustain engagement and foster trust. This research contributes to the broader discourse on human-AI interaction by offering insights into the psychological impact of misinformation and proposing design considerations for enhancing AI-driven communication.