Using a TOPSIS Method to Evaluate and Select AI Chatbots for Improving Customer Service Communication

Abstract

Chatbot has become an innovation for business to connect with customers. People can communicate with technology devices in the same way they would with real people through Chatbots. Traditional Chatbots typically depend on already programmed principles and replies, while AI (artificial intelligence) Chatbots comprehend and dynamically respond to user inquiries utilizing natural language processing (NLP) and machine learning (ML). Chatbots powered by AI have an increased requirement to communicate with customers in a fast and effective way. People can communicate with technology devices like they were speaking to a real person, which are software programs that simulate human conversation which can be texts or speeches. Many criteria quantitative criteria, including frequently asked questions (FAQs), security, brands, improving efficiency, and enhancing engagement, etc., and quantitative criteria, including cost, bot analytics built-in templates and customer relationship management (CRM), etc., need to be considered when evaluating AI Chatbots for companies to enhance customer service. Moreover, criteria may have different importance. Therefore, evaluating AI Chatbots is a MCDM (multiple criteria decision making) problem. Many companies do not know how to select the most suitable one to serve their customers. To address this issue, the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution), one of MCDM approaches, is used to evaluate AI Chatbots; and criteria weights will be produced by applying BWM (Best Worse Method). A numerical example will be used to present feasibility of the used method, and a comparison will be conducted to display its effectiveness.