Developing an AI-Driven Chatbot for Enhanced College Website Support Using Machine Learning

With the emerging technological revolutions, the higher education institutions are integrating Artificial Intelligence (AI) to enhance their website support and user experience. A GPT-2-based chatbot has been developed to assist students, faculty, and stakeholders in navigating the college websites easily. The objective of this research study is to support college websites by interacting with user queries and predicting the cut-off mar of the students based on their academic performance. This AI-driven chatbot employs machine learning and Natural Language Processing (NLP) techniques to address the inquiries regarding admissions, course details, academic resources, administrative procedures, and campus life. Utilizing deep learning techniques, the developed chatbot delivers comprehensive and contextually relevant responses, focusing on Q&A interactions. The chatbot, built upon the GPT -2 model by OpenAI, is skillful at generating human-like text and serves various applications, including customer support and information retrieval systems. Particularly, it specializes in predicting admission cut-off marks, employing regression models such as Linear Regression, Decision Tree Regressor, SVM Regressor, Random Forest Regressor, and XGBoost Regressor. These models consider various factors such as joining year, quotas, previous cut-off lists, department preferences, board exam difficulty, job market demands, and academic performance. The performance evaluation metrics like Mean Squared Error (MSE), Root Mean Square Error (RMSE), and R-squared are utilized to assess the predictive accuracy of the proposed chatbot. By performing a thorough analysis of historical student data, the chatbot provides users with detailed answers and accurate forecasts regarding future academic performance, thereby enhancing the overall user experience of educational websites.