This study investigates the role of artificial intelligence (AI) in mediating intercultural sensitivity among media consumers through their engagement with films and series. Drawing upon a quantitative survey of 385 participants from diverse cultural backgrounds, this research applies multiple regression and ML algorithms including Random Forest, SVM, and Gradient Boosting to predict levels of intercultural sensitivity based on viewers' AI-mediated media consumption patterns, algorithmic recommendation engagement, and cultural exposure variables. Results indicate that AI-recommended media consumption frequency (β = 0.42, p < .001), cultural diversity of content consumed (β = 0.38, p < .001), and critical reflection on media portrayals (β = 0.31, p < .001) are significant predictors of intercultural sensitivity. The RF model achieved the highest predictive accuracy (R2 = 0.74, RMSE = 2.31), outperforming both linear regression (R2 = 0.61) and SVM models (R2 = 0.68). Implications for curriculum integration, media platform design, and cross-cultural communication are discussed.
This study examined the mechanisms that shape consumer engagement in Large Language Model enabled environments by integrating statistical and data driven analytical approaches. Primary data were collected from users with experience in interacting with LLM driven systems. Exploratory Factor Analysis identified the core dimensions underlying engagement related perceptions, while Multiple Regression Analysis examined the influence of technological, psychological, and experiential factors on consumer engagement. Machine learning techniques including classification, clustering, principal component analysis, and feature ranking were employed to enhance predictive accuracy and interpretability. The findings revealed that user motivation, perceived social presence, and trust in the system emerged as dominant drivers of engagement. The study contributes to a deeper understanding of consumer engagement dynamics in intelligent conversational environments and offers practical insights for effective LLM based interaction design.