Study on the Continuous Reading Intention of Classical Novels Based on Random Forest

Promoting the popularization and reading of China's classical novels plays an indispensable role in promoting the exchange, inheritance, and development of Chinese traditional culture and strengthening the cultural self-confidence of the people. Therefore, this paper collects 535 representative sample data, including the popularity of novels, language style, theme of works, and other latent variables, and constructs a random forest model by using the score of 5-level Likert scale to explore the influence of these factors on people's willingness to continue reading classical novels. After the preliminary analysis of the data by Python language tools, it was found that the model effect was not satisfactory, so the SMOTE algorithm was used to oversample the data set and optimize the original model, and the recall rate of the final model prediction reached 86%. Based on the order of importance of influencing factors, it is concluded that the spiritual value provided by the novel is one of the important factors that people are mainly concerned about. This paper puts forward some practical suggestions from the perspectives of content themes, reading methods, and communication channels, which provide theoretical references and solutions for promoting the popularization and popularization of China's classical novels.