Abstract
Neurological, behavioral, and cognitive problems in teenage students are rising day by day. It is very important to handle these issues by gathering information from public opinion. The distribution of public opinion information in student work is unsystematic, and it is difficult to extract the needed information intelligently. An intelligent extraction algorithm of public opinion data from student work is proposed in this research and is based on human–computer interaction, machine learning, and computational techniques. In the student work, a fuzzy semantic autocorrelation mapping feature set of public opinion information is developed together with a spatial structural model of data semantic distribution features. The statistical feature quantity of semantic similarity of the public opinion data is retrieved from the student work, and the semantic ambiguity is decreased. Analyses using adaptive learning and machine understanding and human–computer interaction are used to process it. In the human–computer interaction machine understanding center, the processor adjusts the grid partition of public opinion information of the student work according to the difference of statistical features, then constructs the feature decomposition model of student behavior, and then performs context mapping. Finally, the semantic analysis is carried out to analyze the student behavior based on the cognitive study. The simulation outcomes demonstrate that the proposed method is computationally inexpensive, has low time complexity, and has real-time monitoring ability of public opinion information on student behavior.