Media convergence has changed the environment in which ideological and political education is carried out in higher education. As students increasingly receive information through social media, short-video platforms, and other digital channels, fixed teaching approaches are often not flexible enough to respond to differences in media exposure, engagement, and feedback. To address this issue, this study proposes a dynamic framework for modeling and updating ideological and political education under changing media conditions. The framework combines pathway generation, adaptive adjustment, and outcome evaluation, and further uses feedback signals to refine pathway selection during implementation. Experimental results on four datasets show that the proposed method consistently outperforms baseline models. The largest relative gain appears on the Student Ideological Development Dataset, where the F1 Score improves by 1.22 percentage points over the strongest baseline, rising from 87.34% to 88.56%. The best absolute result is obtained on the Convergence Media Impact on Student Beliefs Dataset, where the model achieves 91.15% Accuracy. These results indicate that ideological and political education can benefit from a framework that remains responsive to media-driven change while preserving alignment with educational goals.
