Sentiment Analysis in Dialogue Systems

More and more companies are choosing to automate various aspects of their customer service using chatbots. While these chatbots are still in their technological infancy, they currently provide useful customer service to many people around the world. They will continue to become more desired by companies as a single chatbot system can engage millions of customers with minimal scaling costs. In these many interactions, there is a substantial amount of potential information to extract. This project focuses on extracting user sentiment information from a large set of chatbot-customer interactions. The ultimate goal of this project is to develop a module that collects and summarizes customer’s sentiment about the company’s products and services as well as their overall sentiment when engaging with the chatbot. Ideally, if successful, the information generated by our sentiment analysis module can be used by companies to more efficiently identify and handle customer issues.

Paul Adrien Briggs
Faculty Supervisor: 
Graeme Hirst
Partner University: