Research on the Pair Programming Partner Recommendation Method Based on Personalized Learning Features

Computational thinking is becoming a hot topic of research in education and pair programming is an effective strategy for developing learners' computational thinking. How to provide suitable pairing partners is a key issue to enhance the effectiveness of pair programming learning. This study analyzed the common factors that affect the effectiveness of pair programming, a five-dimensional learner personality learning feature vector model is constructed. A pair programming homogeneous and heterogeneous partner recommendation method combining multiple distance algorithms is proposed. The method collects student questionnaire data to extract student personality learning feature information for experimental analysis. The results show that the proposed method can effectively improve the learning efficiency of pair programming learners.