Contextual Healthcare Chatbot using Deep Neural Network

Sahu, Suryakanta (2022) Contextual Healthcare Chatbot using Deep Neural Network. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (5MB) | Preview

Abstract

As per the popular saying, a healthy society is a wealthy society, hence healthcare is and always will be among the most vital components of any civilization. With our planet's population growing at a 1.2 percent yearly rate, the world's healthcare system is under tremendous pressure than ever. Also, the changing lifestyle, and multifold increase in pollution are adding fuel to this existential crisis. In this strenuous scenario, technology can offer a helping hand in many ways, and one of them is virtual assistant or chatbot systems. Chatbots are a blend of Artificial Intelligence, Natural Language Processing and big Data to provide accurate information on fingertip. As a major percentage of the world's population lives away from a regular medical facility, chatbots can be acted as a lifesaver in many situations by easily accessing them through smartphones. People are also stimulated to use a chatbot for intimate queries rather than visiting a doctor in person because of the anonymity and privacy conferred by chatbots. In this study, a contextual chatbot empowered by deep learning algorithm and natural language processing techniques was developed and the model's performance was evaluated against a Naive Bayes model and numerous state-of-the-art solutions. For training the conversational system, data was gathered from a number of open-source websites like Wikipedia, WebMD etc. This developed solution also has context retention capabilities, which means it retains certain information from a prior query so that the model can respond to subsequent inquiries more efficiently and with less input from the end user. The suggested model is anticipated to assist users with healthcare related enquiries instantly and without the need for an active internet connection. Upon evaluating the model with a number of accuracy metrics, a train accuracy of 98% and validation accuracy of 81% was achieved.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Healthcare; Deep Neural Network; Naive Bayes; Chatbot; Conversational System
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing R Medicine > Healthcare Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	10 Mar 2023 16:06
Last Modified:	10 Mar 2023 16:06
URI:	https://norma.ncirl.ie/id/eprint/6288

Actions (login required)

View Item