Abstract
Al-Emran et al. (2023) found that a fuzzy-set qualitative comparative analysis could influence the adoption of AI Chatbots, which can improve knowledge transfer. However, there is no research about choosing a suitable Chatbot by TOPSIS. To fill this gap, this study applies the fuzzy TOPSIS method to evaluate Chatbot, with criteria weights being determined through the AHP. To address this issue, this study uses the fuzzy Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), a reliable fuzzy multiple criteria decision-making (MCDM) approach, to evaluate AI Chatbots, with the criteria weights set through the AHP method. Since managers often rely on qualitative, language-based values that might conflict when evaluating Chatbot companies, this evaluation becomes a fuzzy MCDM challenge. In this approach, the ranking of options is determined from highest to lowest based on weighted distances from the Positive Ideal Solution (PIS) and Negative Ideal Solution (NIS). The NIS acts as a benefit criterion, meaning “larger-is-better,” while the PIS serves as a cost criterion, meaning “smaller-is-better.” The weights for the two criteria are determined objectively using the AHP method. To simplify the decision-making process, the mean of removals is applied to defuzzify the final fuzzy values of the alternatives (Kaufmann and Gupta, 1985). The formulas used in this defuzzification process are clearly outlined to ensure effective implementation of the proposed approach.
Presenters
Thi Bao Tram NguyenStudent, MSc, Southern Tainan University of Science and Technology, Taiwan
Details
Presentation Type
Paper Presentation in a Themed Session
Theme
KEYWORDS
AI, Chatbot, AI chatbot, Fuzzy Topsis
