Mining learning social networks for cooperative learning with appropriate learning partners in a problem-based learning environment

Abstract

Many studies have identified web-based cooperative learning as an increasingly popular educational paradigm with potential to increase learner satisfaction and interactions. However, peer-to-peer interaction often suffers barriers owing to a failure to explore useful social interaction information in web-based cooperative learning environments. This easily leads to learners being unable to seek appropriate learning partners for facilitating effective cooperative learning. This problem frequently causes poor learning effectiveness in web-based cooperative learning environments. Generally, instructor assigned or learner selected learning peers cannot ensure to compose suitable learning partners for individual learners in cooperative learning environments. A suitable learning partner can help the learner, who is learning in the personal way and encounters the difficulty, to solve problems. Inappropriate learning partners cannot only easily lead to poor learning interaction and achievement, but can also lead to the meaning of cooperative learning being lost. Although many web-based learning systems have already been developed to assist cooperative learning, supporting peer-to-peer interaction in computer-supported cooperative learning (CSCL) is still immature. As a result, this study presents a novel scheme for recommending appropriate learning partners for individual learners utilizing mining of learning interactive social networks in a cooperative problem-based learning (PBL) environment. Results of this study show that the proposed scheme helps encourage learners to interact with learning peers more actively and positively, and facilitates learning performance in a cooperative PBL environment.

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 — 57 citations exist upstream.

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