Computational Intelligence-Driven Optimization of Ideological and Political Education Management Systems in Response to COVID-19 Online Public Opinion

In the context of the COVID-19 pandemic, online public opinion has had a profound impact on the ideological and political education management systems for university students. However, existing management systems often struggle to adapt to the rapid shifts in public sentiment and efficiently process the diverse forms of data generated through social media platforms. To address these challenges, we propose a model that integrates computational intelligence with multimodal data processing techniques, including multimodal fusion, meta-learning, attention mechanisms and reinforcement learning (RL). This model is designed to enhance the adaptability, decision stability and robustness of educational management systems by effectively analyzing and responding to complex and evolving online public opinion. The multimodal fusion enables the system to process different types of data, meta-learning improves the model’s adaptability to new information, attention mechanisms allow the system to focus on key features, and RL ensures that optimal decisions are made in real-time. Experimental results show that our model outperforms existing approaches in key performance metrics, including accuracy, robustness to noise and decision-making efficiency, particularly in the dynamic environment of online public discourse. This research contributes to the optimization of ideological and political education management systems by improving their responsiveness and effectiveness in the face of rapidly changing online public sentiment.