Due to rapid information technology growth, teaching Chinese in higher education has changed, and Chinese literary majors have vigorously evolved. The key teaching difficulties are scalability, individualized teaching, and a lack of resources and methodologies. Research shows individualized education improves topic comprehension, cultural engagement, and learner interest. Fuzzy association rule mining uses fuzzy linguistic values and membership functions to provide more realistic results. Hence, an algorithm, EF-PCL2T, has been proposed to improve personalized Chinese language and literature teaching (PCL2T) using enhanced fuzzy (EF) Apriori association rule mining integrated with the genetic algorithm. Fuzzy Apriori association rule mining identified frequent itemsets with relevant learning patterns and produced applicable association rules from datasets with fuzzy or unclear information, capturing fluctuating itemset importance and providing a flexible representation of relationships to determine student preferences. From fuzzy-related data, a genetic algorithm optimizes skill sets and creates individualized lesson plans considering each student’s competency and preferences for adjusting to personalized teaching tactics. Testing shows that fuzzy enhancement association rule mining for the PCL2T model improves student retention, PET (personalized teaching efficiency), minimal support and confidence update with fuzzy rules, and student involvement compared to other state-of-the-art methods. Students agree that tailored Chinese language and literary instruction is possible. The improvement results show fuzzy rules with minimum confidence levels of 50% to 100%, highly correlated in this model, student retention ratio of 96%, improved assessment grade of various language skills by 40 marks, PTE analysis of 93%, and student involvement ratio of 97%.