Optimizing Customer Feedback Analysis with BERT-Based Sentiment Classification: A Case Study of Toyota Dong Sai Gon

Digital transformation in customer service operations leverages advanced technologies, particularly Artificial Intelligence (AI) and Natural Language Processing (NLP), to enhance the analysis of customer feedback. This study examines the application of sentiment analysis models, focusing on the Bidirectional Encoder Representations from Transformers (BERT) model, in evaluating customer feedback at Toyota Dong Sai Gon. A comparative experiment involving Naive Bayes, Recurrent Neural Networks (RNN), and BERT models is conducted to identify the most effective model for sentiment classification. The findings demonstrate that the BERT model significantly outperforms traditional models, achieving higher accuracy and efficiency. This research contributes to the field by providing a detailed examination of sentiment analysis models and their practical applications in improving customer service operations. The proposed application of the BERT model includes data collection, preprocessing, and integration into existing systems, highlighting its potential in automating feedback analysis and enhancing customer satisfaction.