An Analytical Study of Learner Collaborative Learning Algorithms for Online Education Based on OSPBO-SFLA Algorithm

Currently, the proliferation of online education platforms has democratized access to learning opportunities, which cultivates a globally inclusive and demographically diverse learner population. However, the absence of interpersonal dynamics inherent in offline education creates isolated learning experiences in online environments. This socio-cognitive disconnect manifests through learners' diminished initiative in peer engagement and psychological barriers to proactive virtual collaboration. Moreover, the lack of learning partner communication and common learning atmosphere, result in low learning efficiency and learning persistence and other problems. Therefore, it is necessary to take measures to help learners improve their learning efficiency and performance. Motivated by these issues, our study proposes a new algorithm based on optimization of student psychological optimization-Hybrid Leap-jumping (OSPBO-SFLA), which is used to help learners in Online Education to carry out long-term collaborative learning. The algorithm is mainly based on the collaborative learning mechanism of the Student Psychological Optimization (SPBO), which classifies students and allows them to learn from each other to improve their grades. Firstly, as SPBO has the disadvantage of weak global search ability, this paper proposes to use the Shuffled Frog Leaping Algorithm (SFLA) with strong global optimization ability to optimize. Secondly, this paper proposes four factors to measure students' test scores to help SPBO further classify four types of students. Finally, it is verified through experiments that the OSPBO-SFLA algorithm has faster convergence speed and higher efficiency than the original SPBO, which effectively solves the problem of collaborative learning of online education learners and improves the learning effect and learning persistence of learners.