In this short article I would like to take the opportunity to explore some of the opportunities and challenges facing the education sector with the emergence of the adaptive learning environment.
At the present moment in time adaptive learning environments take advantage of supervised machine learning techniques to deliver content and assessment activities that are personalised and contextualised to meet the needs of each student. In supervised machine learning teachers define the desired set of outcomes that are expected from an adaptive online tutorial and they also provide regular feedback to the adaptive learning environment which enables it to adjust the paths that it takes to reach a teacher's desired outcomes.
As adaptive learning environments improve they will increasingly start to take advantage of reinforcement machine learning techniques. When this occurs the adaptive learning environment will receive feedback from the actions taken by students on a course; and adjust its actions accordingly to meet the desired outcomes that have been set out by the teacher. As reinforcement machine learning techniques become more advanced within the education sector adaptive learning environments will increasingly present students with content and assessment materials with less input from the teacher. This may sound rather disconcerting; and rightly so, because the teacher, in many instances would not be able ascertain why a given set of content or assessment material was being presented to each of her students. However, teachers would take comfort from the fact that their students were progressing well when viewing each student's personal dashboard.
Currently teachers author content and the assessment activities that students access on an adpative learning environment; and teachers also author and shape the behaviour of the numerous algorithms that are to be found in an adaptive SCORM package. Teachers may feel that they possess a high degree of control regarding the content and assessment activities that each of their students engage with when opening an adaptive tutorial. However, what happens when the library of content and assessment activities on a specific topic begins to grow or when the number of students enrolled on a course numbers many hundreds? When this happens teachers will not be able to map all the possible routes that their students could take through a tutorial. Teachers will have no choice but to assign that part of their role to the adaptive learning environment; where the algorithms will search, analyse, assess and present the most appropriate content and assessment material to each student.
The ILT Team at Bolton College is currently researching the impact that this may have on student outcomes; and how it may alter the patterns of behaviour of students and teachers when in the classroom and when they are on the College's adaptive learning environment. One particular area of interest is the adaptive learning environment's ability to search, analyse, assess and present content and assessment activities to each student; and the impact that this has on teaching, learning, assessment and student outcomes. For instance, in the following example, students are randomly presented with one of four tutorials that introduce them to a particular topic on their course. As students complete their respective tutorials they take the assessment activity at the end of the SCORM package and the scores are recorded against each tutorial. Later, as additional students start the SCORM package they are presented with the tutorial that led to the highest average score in the subsequent assessment activity. In this example, the adaptive learning environment has learnt to present the tutorial to students which has produced the highest average score on the assessment activity at the end of the tutorial. Teachers can go onto refine and improve the lesser scoring tutorials before they are placed back into the adaptive learning environment for dissemination.
If we extend the above example we find that adaptive learning environments can also query a student's profile and assign a tutorial that best suits the needs of that student. For example, if a student has declared that he learns better when viewing video content the adaptive learning environment will present the student with the tutorial which utilises video content to showcase a topic. Conversely, if another student prefers active learning they will be presented with a tutorial that prompts the student to engage with the online content through the use of hotspots, drag and drop exercises or game play.
If adaptive learning environments are used in this manner we suddenly discover that content and assessment activities are now being presented to students based on proven empirical evidence which may lead to improved student outcomes.
Developing a content library
In order to take advantage of adaptive learning teachers and educational publishers will be required to move away from authoring a single set of materials for a topic on a course. If adaptive learning is implemented teachers will need to present multiple iterations for any course topic. Some versions of the tutorial will focus on active learning, others would be more passive, some will be more visual and make use of videos to showcase content, whilst others will make use of more text and so on. Multiple versions for a tutorial are authored to accomodate for the different learning styles of students. Teachers may wish to experiment with different modes of delivery - seeking evidence to determine the best delivery model for a given topic.
Buy in from teachers
Adaptive learning environments will subtly alter the way colleagues teach and assess. Teachers who embrace the potential benefits of adaptive learning environments will have to get used to the fact that another agent; namely the adaptive learning environment, will begin to determine the content and assessment activities to present to their students during the online component of their courses. Teachers will need to see evidence of improved student outcomes, improved student retention and higher student satisfaction ratings for their courses if they are to accept the growing use of adaptive learning environments in their institutions.
If courses are delivered partly or wholly online what will the reaction be from students who learn that they are being taught by hundreds and thousands of algorithms or by an adaptive learning environment with little or no input from a qualified teacher? How will the teaching profession react to the increasing use of adaptive learning environments? Will teachers feel that they are being displaced by adaptive learning environments? And how will parents react when they see their children being taught by an adaptive learning environment? These questions, and many more will need to be addressed if adaptive learning environments are to become the norm within the education sector.