A User-centric smart chatbot for managing admissions nuances of prospective students at Bindura University

Author

Chemariki, Tendai.

Title

A User-centric smart chatbot for managing admissions nuances of prospective students at Bindura University

Abstract

The admission process of universities in Zimbabwe is a labor-expensive task due to the involvement of humans. This paper introduces an intelligent system (a chatbot) that can support the admission process by automatically answering Frequently Asked Questions (FAQs), Help navigate the Bindura University website and sharing information related to admissions, Chatbots are programmed software that can reply to human queries in real-time and their requirement and need in today’s world is endless. To make the chatbots as effective as possible, numerous activities need to be completed. I designed a university information sharing and FAQ chatbot to address admissions nuances of prospective students at Bindura University in the academic environment. This chatbot uses Machine Learning (ML) and Natural Language Processing (NLP) to answer questions about Bindura university of science education in an effective and precise manner. Unlike from prior work that usually builds the bot from scratch, I developed the bot by using the Rasa platform. To do that, I employed different combinations of components of natural language understanding to find the best pipeline. I also created and released a dataset in the admission domain to train the bot. The introduction video of the system is also available.

Date

June 2024

Publisher

BUSE

Keywords

Chatbot,

Admissions, Machine Learning (ML)

Natural Language Processing (NLP)

Supervisor

Dr. T. Chikerema,