Educational data mining using chance discovery from discussion board

We present our preliminary research results of identifying serendipitous findings from discussion forums of students in this paper. A text-mining tool called Polaris was used to generate the analytical results in KeyGraph helping teachers assess the effectiveness of teaching and innovation of learning respectively through the visualization of hidden patterns in the online learning environment. Our results show that the serendipitous findings have shown a traceable pattern to predict the academic performance of students. The research findings can lead to adaptive pedagogical designs for teaching and learning by finding hidden patterns and linkages among the students’ serendipitous learning. Both teachers and students can be supported on how to improve teaching and learning with feedbacks from this new tool. Ultimately, the advanced mining technology to assess the students’ knowledge discovery process can create a new approach for transformative learning and teaching in education. Copyright © 2016 Global Chinese Society for Computers in Education.