A New Filtering Model Towards An Intelligent Guide Agent
Mohammed Abdel Razek, Claude Frasson, Marc Kaltenbach · 2004
In E-learning systems, where both helpers (tutors) and learners are separated geographically, finding a reliable helper is one of the most important challenges. Al-though helpers could have a lot of useful information about courses to be taught, many learners fail to un-derstand their presentations. A major part of this paper deals with the following challenges: do helpers have in-formation that the learners need? Will helpers present information so that learners can understand? And can we guarantee that these helpers will collaborate effec-tively with learners? A new technique is filtering ac-cording to helpers ’ credibilities. We define ”credibil-ity ” as the dependability degree of the learners on the information presented by helpers during a learning ses-sion. We propose a guide agent, based on the pyramid model, which can group helpers. This makes it possible to recommend reliable ones. Furthermore, we devel-oped a new statistical metric called Precision Probabil-ity Value. We have used this metric to measure statisti-cal accuracies rather than the mean absolute error.