A Group Decision-Making Method Based on the Experts' Behavior During the Debate

Debate is a process consisting in arriving at a reasoned opinion on a proportion in which individuals must be truly capable of defending their own judgments. It has been used within group decision-making (GDM) problems to help experts make better decisions. However, whether experts engage in a vigorous debate, it can result in the use of aggressive language that may diminish consensus, which is the major objective of GDM. To avoid it, we present a novel method for GDM problems that can identify aggressive comments during the debate by incorporating a classifier based on sentiment analysis techniques. According to the information extracted during the debate, two procedures are developed to assign weights to the experts, which are used to introduce two new consensus measures and to make the final decision. Unlike the existing GDM methods, this new one can take advantage of the information extracted during the debate (i.e., experts' behavior) throughout the decision process, making it in rapport with real-world GDM processes.