<![CDATA[The growing need for efficient, accessible, and context-aware academic support systems has led to the exploration of Generative AI (GenAI) technologies in educational settings. However, existing virtual assistants often lack contextual relevance, adaptability, and user-friendly interaction, limiting their effectiveness in higher education environments. This study proposes a GenAI-based Virtual Assistant (VA) tailored for university-related applications, combining voice recognition, natural language understanding, and text-to-speech technologies to create an interactive and intelligent support system. The proposed work was evaluated through four key testing stages: black-box functionality testing, response similarity analysis, inference time measurement, and user acceptance testing. Black-box testing validated the system’s ability to process speech input, generate accurate audio responses, and provide responsive UI/UX feedback. A TF-IDF cosine similarity analysis across 11 academic departments yielded an average similarity score of 81.86%, demonstrating semantic alignment with institutional content. The system also maintained an average response time of 3.88 seconds. User feedback from 25 participants revealed high satisfaction levels, with scores exceeding 4.0 across all indicators and large T-statistic value. These results confirm the system’s potential as an effective, real-time academic assistant.]]>
Copyrights © 2025
