Authors:
Santi Caballé
1
;
Thanasis Daradoumis
1
;
Fatos Xhafa
2
and
Joan Esteve
2
Affiliations:
1
Open University of Catalonia, Spain
;
2
Polytechnic University of Catalonia, Spain
Keyword(s):
Web-based Education, User Modelling, Grid Computing, Distributed and Parallel Applications.
Related
Ontology
Subjects/Areas/Topics:
Agents
;
Artificial Intelligence
;
Computer-Supported Education
;
Data Engineering
;
Distributed and Parallel Applications
;
e-Business
;
e-Learning
;
Enterprise Information Systems
;
Grid Computing
;
Information Technologies Supporting Learning
;
Internet Technology
;
Ontologies and the Semantic Web
;
Technology Platforms
;
User Modeling
;
Virtual Learning Environments
;
Web Information Systems and Technologies
;
Web Interfaces and Applications
;
Web Personalization
;
Web-Based Education
Abstract:
Learners interacting in a Web-based distance learning environment produce a variety of information
elements during their participation; these information elements usually have a complex structure and
semantics, which makes it rather difficult to find out the behavioural attitudes and profiles of the users
involved. 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, interests, preferences, and so on. This work provides an approach that
can be used to greatly stimulate and improve the learning experience by tracking the students’ intentions
and helping them reconduct their actions that could evolve accordingly as the learning process moves
forward. In this context, user modelling implies a constant processing and analysis of user interaction data
during long-term learning activities, which
produces large and considerably complex information. In this
paper we show how a Grid approach can considerably decrease the time of processing log data. Our
prototype is based on the master-worker paradigm and is implemented using a peer-to-peer platform called
Juxtacat 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
modelling in on-line distance learning.
(More)