CLARE

Participants

• CSDL: Dadong Wan
• Affiliates: NSF

Summary

Knowledge representation is not only fundamental to machine learning, but is also essential to human learning. However, few existing learning support systems provide representations which help the learner make sense of and organize the subject content of learning, integrate a wide range of classroom activities, and compare and contrast various viewpoints from individual learners.

The goal of CLARE research is to construct a useful representation for human learning of scientific literature that also supports useful computational manipulations. The combination of the representation and related computational services should actually lead to improved performance by learners on selected collaborative learning tasks.

CLARE is an Egret-based system designed to investigate issues in computer-mediated collaborative learning. This system provides a data and process model implementing a novel meta-cognitive framework for knowledge construction. CLARE facilitates seminar-style environments for review and critique of scientific literature.

We believe that collaborative learning is an active knowledge construction process and assert that knowledge representation plays an essential role in achieving a high level of collaborative support. Our approach involves the definition of a representational framework, called RESRA, which characterizes the thematic structure of learning and research artifacts. We then developed a computer-based tool, CLARE, that facilitates the use of RESRA for various collaborative learning tasks. Finally, we employed a case study to empirically assess the effectiveness of CLARE and these research claims.

CLARE was evaluated through a case study with sixteen usage sessions involving six groups of students from two classes. The case study included a total of about 300 hours of usage and over 80,000 timestamps.

A survey of CLARE's sessions shows that about 70% of learners think that CLARE provides a novel way of understanding scientific text, and about 80% of learners think that CLARE provides a novel way of understanding their peers' perspectives. The analysis of the CLARE database also reveals that learners differ greatly in their interpretations of RESRA, strategies for comprehending the online text, and understanding of the selected artifact. We also found that, despite the large amount of time spent on summarization, up to 66% of these learners often fail to correctly represent important features of scientific text and the relationships between those features.

Software

Publications

Available at the CLARE Publications Area.

Status

Completed.

Keywords

computer supported collaborative learning