Comparative Analysis of Sentiment Analysis Models for Consumer Feedback: Evaluating the Impact of Machine Learning and Deep Learning Approaches on Business Strategies

In this study, we conducted a comparative analysis of traditional machine learning models and advanced deep learning models for sentiment analysis of consumer feedback, aiming to assess their impact on business strategies. We evaluated the performance of Random Forest, Support Vector Machines (SVM), Naive Bayes, BERT, and GPT models using a comprehensive dataset derived from e-commerce platforms, social media comments, customer surveys, and online forums. Our results demonstrated that while traditional models like Random Forest and SVM achieved decent accuracy, they were outperformed by the large language models, BERT and GPT. BERT achieved the highest accuracy (92.7%), precision (91.3%), recall (94.2%), and F1-score (92.7%), showcasing its exceptional ability to capture contextual relationships in text. GPT also demonstrated strong performance with an accuracy of 91.5%, although slightly lower than BERT. The findings suggest that transformer-based models, particularly BERT, offer significant advantages in processing consumer feedback, enabling businesses to extract more accurate insights for decision-making, customer satisfaction improvement, and marketing optimization. This study emphasizes the importance of adopting deep learning models for sentiment analysis in business contexts while acknowledging the potential limitations related to computational resources. Ultimately, our research highlights the value of sentiment analysis in informing business strategies and enhancing customer engagement.