Managing Consensus Behaviors Via Sentiment Analysis for GenAI-Driven Consumer Services

With the rapid advancement of artificial intelligence/generative AI (AI/GenAI), various industries have undergone significant transformations, particularly in the realm of consumer devices and services. AI/GenAI plays a pivotal role in product purchase decisions by analyzing vast amounts of user-generated information, such as reviews. This article aims to provide new solutions for new energy vehicle (NEV) purchase decisions through AI/GenAI to better serve consumers. First, a genetic algorithm-guided long short-term memory and gated recurrent unit are integrated for sentiment analysis to accurately express the sentiment tendencies through AI/GenAI, with the results being converted into probabilistic linguistic term sets. Second, an enhanced K-means++ and an adaptive three-way clustering algorithm are utilized to ensure the accuracy of clustering results. Third, a model based on confidence and conflict levels to identify the non-cooperative behaviors is established to facilitate consensus among decision-makers. Fourth, during the selection phase, the three-way decision is combined with multiattributive border approximation area comparison methods to obtain the optimal alternatives. Finally, using NEV purchase examples, the proposed methods demonstrate robustness and reliability, showcasing their effectiveness in enabling GenAI-driven consumer services.