An Approach to Developing Instructional Planners for Dynamic Open-Ended Learning Environments

Instructional planning (IP) technology has begun to reach large online environments. However, many approaches rely on having centralized metadata structures about the learning objects (LOs). For dynamic open-ended learning environments (DOELEs), an approach is needed that does not rely on centralized structures such as prerequisite graphs that would need to be continually rewired as the LOs change. A promising approach is collaborative filtering based on learning sequences (CFLS) using the ecological approach (EA) architecture. We developed a CFLS planner that compares a given learner’s most recent path of LOs (of length b) to other learners to create a neighbourhood of similar learners. The future paths (of length f) of these neighbours are checked and the most successful path ahead is recommended to the target learner, who then follows that path for a certain length (called s). We were interested in how well a CFLS planner, with access only to pure behavioural information, compared to a traditional instructional planner that used explicit metadata about LO prerequisites. We explored this question through simulation. The results showed that the CFLS planner in many cases exceeded the performance of the simple prerequisite planner (SPP) in leading to better learning outcomes for the simulated learners. This suggests that IP can still be useful in DOELEs that often won’t have explicit metadata about learners or LOs.