Government informatization model design based on emotional polarity analysis of network media in the context of deep learning

In response to the extensive and complex public comment data within the government system, this article presents an emotion analysis model for government information based on a dual attention multi-layer convolutional neural network (DA-MLCNN). This model exhibits enhanced generalization and higher accuracy, addressing limitations in expression, difficulty with correlation, and low classification accuracy in sentiment analysis of government media public comments. The model processes public comments by training a convolutional neural network, extracting features at each fully connected layer, and sequentially feeding these features into the classifier for comparison. Selecting the low-level fully connected layer activated by the Rectified Linear Unit (ReLU) function as the feature extraction layer yields a higher recognition rate than using the high-level fully connected layer. This study selects the ReLU layer of the AlexNet convolutional neural network model as the feature selection layer and optimizes the training data and classifier construction system. Experimental results demonstrate that the DA-MLCNN visual emotion analysis model achieves higher discrimination accuracy and better alignment with the emotions expressed in online media. The ablation experiment revealed that the classification accuracy of the DA-MLCNN model significantly surpasses that of the basic network VGGNet-16, proving that multi-layer convolutional neural network (CNN) feature fusion fully leverages the complementary advantages of different feature levels, thereby enhancing the effectiveness of sentiment classification