An evolutionary algorithm for forming mixed groups of learners in web based collaborative learning environments

Abstract

Collaborative learning is a widely used technique in learning environments. Regarding the fact that learners vary in different aspects, and these differences affect the quality and quantity of interactions between them, it is important to group learners in a way that they can effectively cooperate. When only one criterion is considered in forming learning groups, it is not very difficult to create the groups manually, but it becomes complicated when more conditions and criteria are considered. Hence, varieties of algorithms have been proposed in order to ease the group formation process. In this paper, a new mechanism for forming learning groups is introduced. The proposed mechanism is an iterative process based on a genetic algorithm. Our algorithm is flexible to the number and type of the attributes. For different contexts, different set of attributes can be used to form learning groups. In fact, the instructor has the facility to choose different set of attributes and rank them based on their impact on forming well-structured groups. In addition, the iterative nature of the group formation process has let us to tune the threshold fitness value used in our GA, after each iteration step. Furthermore, a novel method for evaluating peers and learners is presented in this paper. The designed method discussed in this paper can be integrated into any web-based learning environment that supports collaborative activities. Currently we have implemented it on MOODLE.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 36 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.