Abstract:

Enhancement of technology in education has increased the adoption of e-learning. An on-line connection makes it possible to access thousands of contents in e-learning platforms based on Learning Management Systems (LMSs), which eliminate the barriers of time and space that usually limit traditional teaching. LMSs facilitate the administration, delivery, visualization and monitoring of e-learning contents in a simple and functional way.
There are many LMSs widely used to support learning/teaching activities. In particular, Moodle (Module Object-Oriented Dynamic Learning Environment) is a free, open-source web application for modular internet-based courses. Teachers and students interact in Moodle by means of activities (e.g. lessons, chats, SCORMs, etc.) On the other hand, resources (e.g. text/web pages, links, etc.) optionally provide additional information to the activities. Hence, courses can be created by appropriately combining activities and resources. Moodle is flexible enough to model from small to big courses. However, the lesson is the most adequate activity to define causal and precedence relationships. Moreover, lessons allow teachers to define educational contents in a flexible, logical and progressive way. Although lessons are useful in course definition, their number and order are fixed by the teacher. In other words, the execution sequence, i.e. learning path, may not take into consideration all the students’ needs, as determined by their profiles (background, learning style and goals). On the contrary, the maximum benefit in e-learning is achieved when each learning path is fully personalized.
Curriculum personalization can be faced in several ways with the objective to offer the best contents to the adequate person. We focus on intelligent planning as a valuable formalism to describe actions (lessons) in terms of preconditions (precedence relationships) and causal effects to find plans (learning paths) that entirely fit the students’ profiles. Thus, the integration of intelligent planning techniques into LMSs makes it possible to achieve the greatest possible learning benefits.
The integration of planning into LMSs is not straightforward. We have embedded a planning approach in Moodle to support this personalization. But Moodle (like others LMSs) presents some limitations. Here, we discuss the four main limitations we found and how to solve them. First, complex relationships that usually appear when planning elaborate courses cannot be easily defined in Moodle. We have overcome this limitation by using intermediate dummy lessons that simulate virtual transitions between learning states. Second, the information that students input into Moodle are not always sufficient to exhaustively define their background and learning goals, essential to customize learning paths. Again, our solution implies the creation of dummy lessons that help specify initial/goal learning states. Third, compiling a planning model from Moodle is not intuitive because course properties are not easily available and, thus, a detailed mapping becomes necessary. Fourth, a challenge arises to personalize the visualization and navigation of individual paths to each student. We have faced this by associating personal views to dynamically created groups of students.
As a conclusion, we will show the integrated system that demonstrates the application of our planning approach in Moodle.

Keywords:

e-learning, curriculum personalization, planning, Moodle, learning management systems.