This study presents a user-driven, emotion-aware expert system designed for intelligent consumer targeting within man–machine computing environments. Traditional digital marketing frameworks rely heavily on generalized behavioral analytics, lacking real-time emotional awareness and failing to capture nuanced user intent. To address these limitations, we propose a next-generation AI architecture that integrates multimodal emotion detection—including facial expression analysis, vocal tone interpretation, and textual sentiment mining—into the targeting process. The system employs a hybrid deep learning framework combining Convolutional Neural Networks (CNN) for visual emotion recognition and Bi-directional Long Short-Term Memory (Bi-LSTM) for sequential audio-text analysis, enhanced by a dynamic attention mechanism. Implemented within a modular, Python-based platform, this expert system enables seamless integration with existing digital marketing ecosystems and supports real-time data processing. Experimental evaluations demonstrate a 21.6% improvement in targeting accuracy over behavior-only models and a 92.4% emotion recognition rate on standard benchmarks. Results show increased user engagement, improved personalization, and higher campaign effectiveness. This research contributes to the field of augmented intelligence and expert systems by advancing man–machine interaction and enabling emotionally adaptive consumer profiling for smarter, human-centered digital marketing strategies.
Aziz et al. (Mon,) studied this question.