Abstract
Food public opinion is characterized by its low ignition point, high diffusibility, persistence, and strong negativity, which significantly impact food safety and consumer trust. This paper introduces the Food Public Opinion Prevention and Control (FPOPC) model driven by deep learning and personalized recommendation algorithms, rigorously tested and analyzed through experimentation. Initially, based on an analysis of food public opinion development, a comprehensive FPOPC framework addressing all stages of food public opinion was established. Subsequently, a sentiment prediction model for food news based on user comments was developed using a Stacked Autoencoder (SAE), enabling predictions about consumer sentiments toward food news. The sentiment values of the food news were then quantified, and improvements were made in allocating Pearson correlation coefficient weights, leading to the design of a collaborative filtering-based personalized food news recommendation mechanism. Furthermore, an enhanced Bloom filter integrated with HDFS technology devised a rapid recommendation mechanism for food public opinion. Finally, the designed FPOPC model and its associated mechanisms were validated through experimental verification and simulation analysis. The results demonstrate that the FPOPC model can accurately predict and control the development of food public opinion and the entire food supply chain, providing regulatory agencies with effective tools for managing food public sentiment.