Adaptive learning environments are representative of a new breed of digital services that have emerged within the education sector over the last decade. They have come about because they take advantage of data and the technologies that support data management. The growing use of machine learning and natural language processing will further escalate the development and use of adaptive learning environments within the education sector. The use of these new artefacts will bring about many benefits to students, teachers and educational leaders; but it must be noted that the introduction of adaptive learning environments will also pose many challenges to all stakeholders within the sector. This article seeks to explore (through various scenarios) the use of adaptive learning environments, the benefits that can be derived from them and the challenges that arise from their use.
Scenario 1: The adaptive learning environment takes advantage of a much larger eco-system to deliver differentiated and adaptive tutorials and assessment activities to each student. Many of the behaviours that are exhibited by adaptive learning environments are only possible if they are able to interrogate other datasets within the school, college or university. These include the information held by an institution's registrar office, exams, library, assessment data, a student's editable profile, intended destination routes, course information, the institution's termly calendar and many more. The algorithms that underpin the online tutorials or assessment activities within an adaptive learning environment will query multiple datasets before building and delivering the most appropriate learning materials and assessment activities to each student. If other schools, colleges or universities use the same adaptive learning environment an institution could take advantage of a much larger dataset to inform the services offered by its own adaptive learning environment.
Scenario 2: The ability to offer differentiated content and assessment activities is a key feature in an adaptive learning environment. At Bolton College, the ILT Team has been testing the use of numerous variables to deliver differentiated content and assessment activities to students. General variables such as unique student ID, student name, department or faculty name, course title and course level have all been successfully used. Student specific variables such as entry qualifications, start of course diagnostic test results, learning preferences, on course assessment results, gender, current academic target and more have all been used to successfully deliver differentiated material to each student. One of the challenges for schools, colleges and universities who wish to offer differentiated and personalised content and assessment materials to students is their capacity to create or purchase learning and assessment materials that are differentiated. For instance, the authors of an online tutorial that references learning preferences need to produce multiple sets of the same tutorial to accommodate for visual, kinesthetic or auditory learning preferences. Another challenge facing teachers is their readiness to allow the adaptive learning environment to determine which learning and assessment materials to present to each student. If the library of content for a course is large the teacher may not be able to identify which learning and assessment material has been presented to each student.
Scenario 3: The adaptive learning environment uses historical data to inform the composition and delivery of online tutorials and assessment activities. In this scenario the adaptive learning environment queries historical student records, it assesses the success or failure of tutorials and assessment activities that it has previously presented to students before presenting an online tutorial or an assessment activity to a given student. Teachers and instructional designers will play a significant part by using this empirical data to ensure that online tutorials and assessment activities are routinely amended, revised and improved.
Scenario 4: Student profiling will become common place. Students are profiled from the moment they enquiry about a course at a school, college or university. The student's profile will inform and shape multiple services that are offered or not offered to the student; including academic support, financial support, the offer of courses, progression choices and even the online tutorials and assessment activities that are presented to the student via the adaptive learning environment. The use of student profiling within adaptive learning environments works as follows. In this example, a student enters a course with a particular grade profile. If the student wishes to gain a specific grade on the course in order to progress onto the next course the adaptive learning environment will adapt the online tutorials and assessment activities to enable the student to achieve the target grade. One of the challenges facing educational institutions will be their ability to use student profiling without unnecessary bias or prejudice.
Scenario 5: As well as assessing the behaviour of individual students the adaptive learning environment will also use the behavioural traits of other students before presenting tutorials and assessment activities to each student. This may include the time taken to complete a tutorial or the time taken to complete individual slides within a tutorial, the responses given to set questions within assessment activities, the proportion of students who asked for help during a tutorial or the proportion of students who successfully completed a tutorial.
Scenario 6: As well as providing personalised and adaptive content to students in schools, colleges and universities; adaptive learning environments can also be used to support training for the wider workforce. Training materials can be personalised and adapted according to job title, job role, department, prior education or experience within the organisation.
Scenario 7: One of the most interesting aspects of an adaptive learning environment is its capacity to learn. The adaptive learning environment weights each tutorial and assessment activity and it uses these weightings to inform the composition and delivery of each subsequent tutorial and assessment activity. In this scenario a group of subject specialists may compose a pool of learning materials on a given topic on a course. Over a period of time the adaptive learning environment will learn which of these tutorials improve the grades that students achieve on subsequent assessment activities. Tutorials that lead to improved grades will have a higher probability of being presented to students and vice versa. An adaptive learning environment can also assess which tutorials and assessment activities are best suited for students with different learning preferences. It can therefore query its pool of online tutorials on a specific topic and present the best tutorial that is suited to a student who wishes learn kinesthetically for example. One of the challenges facing teachers is their confidence in accepting the decisions that are being made by the adaptive learning environment in these instances. As teachers develop a better understanding of how their institution's adaptive learning environment makes decisions, they will gradually see it as an indispensable item in their toolkit.
Scenario 8: Adaptive learning environments are ideal platforms for assisting teachers to distribute timely and differentiated content and assessment activities to each student on a course. In this scenario a maths teacher sets a student with a target to pass an equivalent fractions test. The target informs the content and assessment activities that a student sees when viewing the next online tutorial. When the student successfully fulfills the target the teacher or the adaptive learning environment can then apply the next learning and assessment target to the student. The teacher may wish to meet with the student to discuss how he or she coped with meeting the target and how he or she feels about the next learning target. In other circumstances, the teacher may be happy for the adaptive learning environment to acknowledge completion of the current learning target and for it to set the student's next learning target. The latter may be applicable where there are hundreds or thousands of students participating on a given course. If this is the case, students will have the opportunity to progress through the course at their own pace.
Scenario 9: The adaptive learning environment presents tutorials and assessment activities based on the hypotheses or algorithms that it has constructed independently from a teacher. This does not sound as far fetched as it first appears. For instance, if an adaptive learning environment is set a goal of ensuring that 90% of students pass a given tutorial it can adapt the choice of slides and assessment activities; and do so with complete autonomy from the teacher. The choice of slides and assessment activities is not incidental because the adaptive learning environment will use data collected over many days, weeks, months and years before it determines the most appropriate combination of content and questions to put to each student.
Scenario 10: As the previous scenario demonstrates one of the most remarkable aspects of adaptive learning environments is their ability to independently compose tutorials and assessment activities before presenting them to each student. The adaptive learning environment draws upon a large library of content and assessment activities. Over a period of time it gathers and assesses the data gathered from the many interactions that have taken place between students and the content library. Since each element within the content and assessment library is essentially a tagged entity or object within a database; and since each object carries with it a weighting the adaptive learning environment can construct a tutorial or assessment activity with no intervention from a teacher or an instructional designer. An adaptive learning environment's ability to autonomously author learning and assessment materials will progress if we see further advances in machine learning, further developments in natural language processing and greater access to online content libraries.
As you can see through these scenarios adaptive learning environments have the potential to fundamentally alter the way teaching, learning and assessment materials are presented to students. Teachers will need to get used to another agent supporting them in the classroom; namely the adaptive learning environment - especially if the agent becomes more autonomous in its decision making.