Supporting the development of collaborative problem-based learning environments with an intelligent diagnosis tool

Problem-based learning (PBL) has been implemented for years in lots of countries and the achieved performance is plausible. However, the implementation of PBL course often needs a lot of human resources; the instructors often need offering instructions to the learners intensively. As the modern computer science and the Internet gains wide popularity around the world, e-learning is taken by the learners as an important study aid and thereby lightens the burden of the instructors. In this research, we incorporate the PBL activity into an open software e-learning platform, Moodle, and a learning diagnosis tool is added in the platform to alleviate the loading of the instructors. The learners’ transcripts posted on discussion board and chatting room are first preprocessed by the learning parameter extraction module to truly reflect the learners’ planning on the solutions to the designated problem. The extracted parameters are further fed into a classification algorithm to examine the quality of the learners’ suggestions and some appropriate feedback will be issued to the learners/instructor if needed. The experimental results show that the text mining and machine learning techniques used in this work are effective in automatically providing useful feedback for the learners to progress through the ill-structured problem solving.