Random Forest for Predicting Ethical Dilemmas of Artificial Intelligence of Junior High School Students

Artificial intelligence (AI) + Education brings education opportunities of junior high school students but also triggers potential ethical dilemmas. Random forest is a machine learning algorithm that performs well in prediction tasks due to its strong feature screening and noise resistance capabilities. Therefore, we construct a prediction model of ethical dilemmas of AI of junior high school students based on random forest. First, we distribute the questionnaires to 362 junior high school students from two middle schools to collect their scores of the four dimensions of ethical dilemmas. Then, data preprocessing is carried out to clean the collected data and transform non-numerical features into numerical features for subsequent analysis. In the model training stage, the initial model parameter ranges. Next, the cross-validation performance of each parameter on the training set is calculated through the grid search technique, and these parameters are continuously adjusted to optimize the model. Finally, the trained model is verified using the test set to determine whether the model can accurately predict the ethical dilemmas of AI for junior high school students. The experimental results show that the constructed model is highly accurate.