Dynamic Generation of Personal Learning Environments: A Conceptual Framework

For the past ten years, I have been researching about personalisation in web-based learning environments. In short, I wanted initially to probe if an automated system could be built that would propose learning resources to a learner based on his or her personal learning preferences.

It is important to note that the personal learning preferences of a learner can encompass a number of attributes and factors ranging from his learning needs, level of education, the subject area, his preferred learning and cognitive styles etc. The list is non-exhaustive.

During the period of inquiry, a simple personalisation framework was conceived and developed and it featured a fuzzy algorithm to select learning resources that would form a learning path for a student given his preferred information processing styles based on the V-A-K model. 

Looking at the outcomes of the research which demonstrated that students performances did not necessarily improve by providing them with content that is matching their supposedly preferred styles, a new perspective opened up though in the possibility to dynamically generate a learning path for a student based on his preferences from the pool of open learning resources that exist over the web. 

My research started about a decade ago when adaptive intelligent systems were under investigation. The web evolved to Web 2.0 where the learners and the teachers had important roles co-creators and consumers of knowledge while in the era of Web 3.0 the intelligent web has surfaced. 

In a brief discussion with a colleague in an international conference on the research, we agreed that a shortcoming of the personalisation framework that was developed was about the enormous effort that seems to be needed firstly for developing multiple content representations, and second tagging of the learning objects. It would be costly both in terms of efforts and resources to develop the learning objects and then time-consuming to tag them appropriately based on the personalisation model. 

In the current era of Web 3.0, both of the pertinent issues as described above seemed to have been automatically resolved. The worldwide web is flooded with Open Education Resources and repositories keep growing everywhere. Most content need not be developed or redeveloped. A simple search on the web will reveal multiple representations of content in terms of modality, level of study, type of learning approach and the list goes on.

From the figure above, we can see that the e-learning platform becomes mainly a portal for the dissemination of personalised learning paths. These paths can be generated based on a pre-selected set of variables representing individual differences (not necessarily limited to learning styles). The e-learning platform is intrinsically linked to the World Wide Web and to specific open courseware repositories, digital libraries and other resources.

Regarding the tagging process, an extension of metadata of such resources can easily be done and instead of one teacher needing to tag resources, many of these resources can already contain a significant amount of metadata information relevant to the personalisation we want to achieve. Once the algorithm is applied, a personalised learning path can easily be generated for any learner in a course where the system automatically looks for content from a pre-selected list of repositories. This element will definitely constitute an area for future investigation.