<![CDATA[This study aims to evaluate the use of a Telegram-based question-answering chatbot for accessing nutrition information using the UTAUT and TAM approaches to measure user intention and behavior. The system utilizes LangChain and Large Language Models (LLMs) to deliver rapid and precise nutrition-related replies. Validity and reliability assessments were performed to confirm that the measurement equipment exhibited optimal consistency, with Cronbach’s Alpha values surpassing 0.7. The multiple linear regression results demonstrate that Effort Expectancy (EE) and Social Relationship (SI) significantly affect Behavioral Intention (BI), whereas Performance Expectancy (PE), Perceived Usefulness (PU), and Perceived Ease of Use (PEOU) exhibit no substantial relationship. The findings indicate that usability and social impact are more pivotal in enhancing users' propensity to use the chatbot than system utility and efficiency.]]>
Copyrights © 2026
