User modelling in on-line distance learning is an important research field focusing on two important aspects: describing and predicting students' actions and intentions as well as adapting the learning process to students' features, habits, preferences, and so on. The aim is to greatly stimulate and improve the learning experience. Indeed, on the one hand, students' intentions may change during the realization of learning activities and thus their actions evolve accordingly as the learning process moves forward. On the other hand, adaptive systems can effectively plan and design appropriate learning tasks according to students' features, habits and interests with the aim of facilitating the achievement of the learning goal. In this context, user modelling implies a continuous processing and analysis of user interaction data during long-term learning activities, which produces large and considerably complex information. As a consequence, processing this information is costly and could require computational capacity beyond that of a single computer. In this paper, we show how a grid approach can considerably decrease the processing time of log data of on-line distance educational Web-based systems. Our prototype is based on the master-worker paradigm and is implemented using a peer-to-peer platform running on the Planetlab nodes. The results of our study show the feasibility of using grid middleware to speed and scale up the processing of log data and thus achieve an efficient and dynamic user modeling in on-line distance learning.

Peer Reviewed