Digital Twin-Enhanced Sentiment Analysis for Targeted Marketing Optimization

This research presents a digital twin-enhanced sentiment analysis model for optimizing targeted marketing strategies using multi-objective optimization. By integrating BERT-based sentimentanalysis, digital twin simulation, and evolutionary algorithms, the framework dynamically adjusts marketing actions to maximize engagement, minimize costs, and enhance personalization accuracy. The proposed Greedy Man Optimization Algorithm (GMOA) outperforms traditional methods, achieving superior results in consumer targeting and cost efficiency. Findings demonstrate the effectiveness of AI-driven adaptive marketing, providing a scalable and ethical approach to modern digital advertising.