AI-Based Student Assistance Chatbot Using Natural Language Processing and Machine Learning

Abstract

This study presents the development of an AI-based student assistance chatbot using Natural Language Processing and machine learning techniques. The system is designed to classify student queries into four categories: academics, examinations, mental health, and time management. A dataset of 200 queries was manually created to ensure originality and relevance. Text preprocessing was performed using normalization and stop word removal, and feature extraction was carried out using TF-IDF vectorization with n-gram features. Three machine learning models—Logistic Regression, Naive Bayes, and Support Vector Machine—were implemented and evaluated. Experimental results show that Logistic Regression and Support Vector Machine achieved the highest accuracy of 82.9 percent, outperforming Naive Bayes. The system was further enhanced with a web-based interface using Streamlit and AI-based response generation for dynamic interaction. The results demonstrate that the proposed approach is effective for real-time student query classification and support.

Ähnliche Arbeiten