Answers are grounded in this paper and cite their sources.
Prospective students and their parents need quick and reliable answers about admissions, fees, courses, eligibility, scholarships, hostels and placements, yet most college help desks work only during office hours and depend on staff who answer the same questions again and again. This paper presents the design and development of an AI-Based College Enquiry Chatbot System that answers such enquiries automatically through a conversational web interface that is available round the clock. The system combines natural language processing with machine learning. Each user message is pre-processed (tokenisation, normalisation, stop-word removal and lemmatisation), converted into TF-IDF and sentence-embedding features, and mapped to one of twelve enquiry intents by a Support Vector Machine classifier. A dialogue manager then retrieves the verified answer from a structured knowledge base, so that fees, dates and eligibility rules are never invented by the model. Queries classified with low confidence are passed to a fallback module that suggests related questions or forwards the enquiry to college staff, and an administrator dashboard allows the knowledge base to be updated without changing any code. Naïve Bayes, Logistic Regression, Random Forest and SVM classifiers were compared, and the embedding-based SVM gave the best cross-validated accuracy of 94.2% with an average response time below half a second. The proposed system reduces the workload of the admission office, shortens the waiting time of applicants and offers a scalable, low-cost decision- support tool for educational institutions.
No takes yet. Share an insight, caveat, or question.
Verma et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: