Graphical Visual Analysis of Consumer Electronics Public Comment Information Mining under Knowledge Graph

With the continuous development of information technology, information in electronic products has shown explosive growth. Data mining for these reviews can better visualize them. To find the information you need quickly and accurately from the vast amount of information, this paper analyzes the algorithm process of commenting on the information sentiment visualization from the theoretical knowledge of Knowledge Graph and information sentiment visualization to quickly and accurately find the required information from the massive information. The knowledge classification model based on Graph Convolution Network (GCN) is discussed. A visual analysis model of comment information sentiment is constructed based on the Knowledge Graph GCN classification model. The model’s performance is verified by the comparison experiment of the Relation-GCN (R-GCN) classification experiment and link prediction under different datasets. The results show that in analyzing the mobile comments of a shopping website, the sentiment visualization of the comment information can help users decide whether to buy consumer electronics. According to the entity classification dataset, the accuracy of the model constructed here has reached 80%. In addition, the associated prediction data sets are comparatively analyzed. It is found that the R-GCN model is significantly better than the GCN model, and its Mean Reciprocal Ranking is at least 14.6% higher than that of the GCN model. Therefore, the visualization of comment information based on the Knowledge Graph here can provide new ideas for the collation of comment information and the construction of the Knowledge Graph.