One-to-one complementary collaborative learning based on Blue-Red trees and performance analysis for social network

In this paper, we used the Rule-Space Model to infer reasonable learning effects represented as Blue-Red trees and their definitions by analyzing all learning objects of courses within a system. We can derive nine learning groups of social network grouping algorithms and classify particular Blue-Red trees that belong to a specific learning group from previous definitions. An example for a course with the Rule-Space Model analysis of learning objects is illustrated and proved. From this example, thirty-six learning effects as Blue-Red trees can be created that are grouped under nine learning groups of social network, and inferred one-to-one complementary collaborative learning group algorithms of strong learning. Thus, the algorithms within the system will recommend those specific Blue-Red trees that satisfy one-to-one complementary collaborative learning group of strong learning and analyze these learning performances of all Blue-Red trees. They will be the basis of verification for one-to-one complementary collaborative learning.