An Analysis of Mouse Trajectories to Ascertain Hesitation in Solving Word-Reordering Problems

We have been developing a Web application that will help both teachers and learners notice the crucial aspects of solving word-reordering problems. Evaluation systems most computers employ deal with only results of the answers reached by learners without looking into the process by which the answers are produced. It will be insufficient to ascertain learners’ understanding level because correct answers may well include lucky hunches, namely accidentally correct but not confident answers. In order to differentiate these lucky answers from confident and correct ones, we have developed a Web application that can record mouse trajectories during the performance of tasks. By analyzing the recorded trajectories, our Web application will be able to identify the accidentally correct answers and notify learners of the fact that they do not fully understand the important factors tested by the problems. After a brief description of this Web application, we illustrate the way to classify confident and not confident answers as a whole in terms of mouse trajectories, and then we discuss how to apply the classification method to individual learners.