AI-Driven Targeted Advertising Systems Enhancing User Experience in Mobile Social Media Platforms

In the modern digital economy, targeted advertising is essential for mobile social media platforms, helping advertisers reach specific audiences more effectively. However, current AI-driven systems face issues like ad fatigue, privacy concerns, and biased targeting due to suboptimal algorithms, which compromise user experience and ad efficiency. To address these challenges, this study proposes the HBP-AI-TA (Hybrid Behavioral Profiling AI-Driven Targeted Advertising) model, a framework that enhances ad accuracy and relevance through hybrid behavioral profiling techniques. Leveraging deep learning, collaborative filtering, and user behavioral analysis, the model integrates real-time bidding, contextual targeting, and feedback loops while improving user privacy. This hybrid approach reduces algorithmic bias and ad fatigue, creating a seamless user experience. Through data collection from user interactions, behavioral analytics, and AIdriven ad prediction, the HBP-AI-TA model demonstrated an accuracy of 96.77 %, precision of 95.01 %, recall of 93.0 %, and F1 score of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 4. 1 9 \%}$</tex>, outperforming traditional models. Overall, the model provides a valuable solution for enhancing targeted advertising, benefiting both users and advertisers by improving precision and personalization.