Predicting and Interpreting the Matrix Effect of Multi-Platform Audiovisual Content Distribution Using Explainable Artificial Intelligence

The rise of multi-platform audiovisual content distribution has fundamentally transformed the contemporary media ecosystem. Micro-series, short videos and AI-assisted audiovisual works are increasingly disseminated through networked structures rather than existing as standalone media objects. Although early research has recognised the synergistic potential inherent in cross-platform effects, empirical studies capable of predicting and explaining these effects based on matrix effects remain limited. More specifically, most traditional statistical techniques struggle to account for the non-linear and interactive processes underlying coordinated distribution strategies. To address this gap, this study proposes an explainable artificial intelligence (XAI) framework for predicting and interpreting matrix effects in multi-platform audiovisual content distribution. Using an empirical dataset based on real-world distribution cases, this study employs machine learning models to predict audience attitudes, emotional responses, and reception outcomes. By combining feature importance analysis with SHAP-based explanation methods, it identifies the relative contributions of platform coordination, content structural features, and annotated narrative attributes. The results indicate that the explainable AI model not only outperforms benchmark statistical methods but also provides interpretable insights into the mechanisms shaping matrix effects. Among the identified predictors, the intensity of cross-platform coordination and narrative coherence were found to be the most influential variables. In addition to enhancing predictive performance, this study demonstrates the value of explainable artificial intelligence (XAI) as an analytical method for examining the complex dynamics of distribution within applied media contexts. The proposed framework provides methodological support for future research and offers practical value for optimising multi-platform audiovisual distribution strategies.