Research on Adaptive Learning Mode of Folk Education Driven by Big Data

In response to the problems of low resource utilization, short learning time and poor test scores in the adaptive learning mode of folk education, this study proposes a big data-driven design method aimed at improving the efficiency and effectiveness of folk education, while exploring its potential applications in personalized education and cultural inheritance. By improving the Apriori algorithm to mine folk education data, combined with stepwise regression analysis to complete data statistics and using long short-term memory networks to predict learners’ levels. On this basis, a personalized resource recommendation model including entity embedding, graph attention, learner interest modeling and DDDQN module is constructed and an adaptive learning mode is designed. The experimental results show that this method can significantly improve the utilization rate of folk education resources to 98.2%, with an average learning time of 67.3 h and an average test score of 86.2 points, proving that it not only optimizes the learning process, but also has the potential to be widely applied in practical educational environments and cultural inheritance.