Crafting a Personalised Agent-Oriented Mobile E-Learning Platform for Adaptive Third Level Education

Introduction

The internet is the medium for distributing content more efficiently anywhere, anytime. Learning in the 21^st century is becoming ubiquitous and personalised (Bates 2000). Distance learning systems and e-learning has become a great challenge and focus of many research teams in recent years. Several e-learning tools are now enhancing second and third level learning experience in Asia, Africa and Europe (Keegan 2008). Quality pedagogical techniques enhance students’ abilities and save students time when they acquire new skills and knowledge.

There is a huge demand for distant learning; the traditional learning system is too restricting for modern students. These students need to multi-task and manage their time. These students also have short attention span hence they cannot focus on a single task for a long period of time in a single space. Modern students have to work part-time in order to meet end meet such as upkeeps, school fees, etc. In order to balance work roster and college timetable, students prefer a flexible timetable, they enrol to fewer modules hence the duration they spend to get a degree is extended. Research showed that 70% of the Australian students work an average of 14.5 hours per week and American third level students work between 5-60 hours per week. Thirty-three percent full-time students and forty-seven percent part-time students admitted that they often and sometimes miss lectures and practical sessions (Misfud et al 2005). The same education systems are mainly based on client-server or peer-to-peer architectures, which have shortcomings such as poor scalability and low availability. Another approach such as service-oriented architecture encapsulates e-learning contents (Harrier, 2002, Pankratius, 2004, Vossen, 2003) inside a Web service to improve interoperability and reusability (Pankratius et al, 2003). This approach benefits education systems; contents are made available on the Web in different formats; the Web services can provide functionality that extracts and present these contents (Pankratius, 2003).

Personalisation is another shortcoming of the current e-learning systems (ELS) and one of the strong claims of the work presented in this chapter. In the previous years, some ELS introduced useful suggestions to support students’ lesson sessions, monitor student’s progression and consider students’ learning styles (Ayoola 2008). An extracted suggestion can be content-based, recommending a similar course based on students’ browsing history or search query. This collaborative filtering is carried out by searching for similarities between students and recommending similar modules (Garruzzo et al, 2007).