A Personalized Online University Chatbot Using NLP Techniques

Abstract

The objective of this project is to develop a Personalized Online University Chatbot. This report explores different techniques used for the university Chatbot. Different stages involving chatbot processing like the collecting the data, pre-processing stage, feature extraction, training and testing the model will be studied and discussed. Finally the end product of the algorithms will be written in the application software called PyCharm. This project uses the Natural Language Processing technique to develop the software. The main advantage of using the NLP it provides features extraction and help to develop the desirable Chatbot [8]. Different models of NLP are discuss and TensorFlow technique was used due to its’ capability of an end-to-end open source machine learning platform for everyone. Discover TensorFlow's flexible ecosystem of tools, libraries and community resources. After trials and errors, a suitable set of training and testing parameters are define and NLP structure is created. The system first proceeds with collecting data for the queries then it perform the data pre-processing, after the pre-processing the model will be train and test for the prediction and the features extraction are also performed in the process. This system is designed to customize the network for multiple user. Recommendations for future development and conclusions are also included in the report