<![CDATA[The transformation of academic administrative services in higher education requires intelligent systems to automate routine information delivery. This study presents a web-based chatbot using Natural Language Processing (NLP) and the Multinomial Naïve Bayes (MNB) algorithm to enhance administrative services. The system classifies user queries into 20 intent categories and provides real-time responses. Training and testing were conducted using labelled text data. The model achieved 93.62% training accuracy and 63.38% test accuracy, indicating potential overfitting due to the limited variety of test data. Evaluation metrics showed 63% precision, 60% recall, and a 61% F1-score, reflecting stable classification performance. User Acceptance Testing (UAT) was conducted with students and administrative staff, showing acceptance rates of 83.5% and 84%, respectively. These results indicate strong usability and relevance of the chatbot in academic contexts. The system integrates text classification, NLP, and user evaluation within a single framework to address repetitive administrative tasks. This research contributes a practical solution tailored to the needs of academic institutions by combining machine learning techniques with direct user evaluation. The chatbot provides faster and more consistent access to academic information, thereby reducing dependency on manual administrative processes. Future work may enhance classification accuracy by utilising richer datasets and alternative algorithms.]]>
