What is personalised learning?

Foundations

The following paper argues that the traditional LMS/VLE has been challenged...

Key terms

Learning analytics: Learning analytics is the collection and careful...

Personalised learning is when you create a special approach or learning path for one or more students. This can be as simple as providing an extra credit assignment, or as complicated as using technology tools to enable access to additional content types based on student preference.

Personalised learning

The individualised shaping of teaching and learning environments to meet the learning needs of students.

Developing a personalised learning environment

Imagine being able to detect when your students are having trouble working through assignments, tests, and quizzes, and being able to direct their attention to resources which would be beneficial to their learning at that exact point in time. Even without complex adaptive learning technology in place, you probably have access to student performance data that can help your students perform better when taking tests and quizzes, and completing written and project-based assignments.

adaptive learning

The computerised review and analysis of student profile and process data, which results in the immediate presentation of a more personalised learning environment.

The key step in developing a personalised learning environment is mastering how to think about the elements you would put in place based on student preference and performance. You can start by building resources into the feedback you provide to your students within all assessments. This requires that you evaluate the obstacles that typically get in the way of student learning in your classes, and plan in advance to model personalised learning that would help learners overcome these obstacles if needed.

In the following activity, click 'Next' to move through the screens and review and reflect on a process to model a personalised learning environment using any technology tools you have available.

The following paragraphs will give you an opportunity to review and reflect on a process to model a personalised learning environment using any technology tools you have available.

Useful links

Learning analytics are often used by academic administrators to make...

Set up a time to review student progress

Set aside time on a regular basis to evaluate student progress against set objectives, and review how often students are logging into the online classroom. Set personal reminders to review overall performance and student grades at the end of each graded learning activity.


Establish a review and personalisation process

Let your students know that you are willing and able to provide personalised learning through additional or alternative activities. Consider offering options at the start of the course for students to choose from different content types to meet their learning needs.


Provide feedback

Tell your students how they are doing. They don't just need to know where they are and where they're going, but also how they're progressing along their learning path. Use announcements and email to remind students of deadlines and progress against course milestones.


Ask for guidance

Reach out and survey your students about content and learning activity preferences. For example, some students may state a preference for learning with visual and audio cues. Whilst it is important to include a broad range of content types in your course, you can adapt course content and learning activities as the course progresses to incorporate particular elements valued by your students.


Know your students

Review student profile data including typical course access times to adjust schedules for deadlines that can be met. Check to see if they are taking other classes, and when projects and discussion forum posts are typically due.


Know your LMS/VLE

Check reporting and automated messaging features within your LMS/VLE. See if you can send automated messages based on deadlines, submission of projects, or performance against set milestones.

What do we mean by adaptive learning?

Useful links

'Learning to adapt: A case for accelerating adaptive learning in higher...

Adaptive learning is a type of personalised learning. It's an approach to online teaching that focuses on providing the learning content most suited to the students' needs. The data-mining technology supporting this approach relies on learning analytics – which presents data related to how students are accessing content – and adjusts in real time to provide access to the types of content and resources students need at specific points in order to advance through their lessons and courses. Some of these learning approaches are facilitator driven, reliant on the teacher's analysis or review; others are driven by assessment, with changes to content, delivery, etc. directed by the learning analytics' interpretation of student performance.

learning analytics

The use of statistical analyses of rich data to inform decision making in education.

Even if your institution is not using personalised or adaptive learning environments, it is important for you to understand the reasoning behind them, and the tools that are being used to support their successful implementation.

In the following activity, you will be presented with a number of defining characteristics for two types of adaptive learning approach – facilitator driven and assessment driven. In each case, click on the characteristic and then click on the column in which you think it belongs.
You will now be presented with a number of defining characteristics for two types of adaptive learning approach – facilitator-driven and assessment-driven. Decide which of the two types of learning approach the characteristic fits, then continue on to check if you are correct and reflect on some feedback.

Characteristics

  • Students are given access to more difficult content based on their performance and aptitude within the LMS/VLE
  • Data on learner profiles determine preference for content delivery modes and content adjusts on an individual student basis
  • You review the student performance dashboards included in your LMS/VLE to review student performance and adapt your course materials in response
  • You review course access and performance data and provide customised guidance and feedback to low performing students
  • Content is conditionally released based on performance against set established conditions within the LMS/VLE
  • You map learning objectives to course milestones to check on student progress, and adapt course content along the way as needed
  • Recommended changes to student course selection or programme registration are provided based on correlation of student profile and performance data
  • You survey students, monitor preference for content delivery modes, and provide alternative content types based on feedback
  • Performance data from students struggling with concepts automatically trigger the availability of tutoring tips and additional learning resources

Now check if you are correct and consider some feedback.

Facilitator-driven adaptive learning

  • You review the student performance dashboards included in your LMS/VLE to review student performance and adapt your course materials in response
  • You map learning objectives to course milestones to check on student progress, and adapt course content along the way as needed
  • You review course access and performance data and provide customised guidance and feedback to low performing students
  • You survey students, monitor preference for content delivery modes, and provide alternative content types based on feedback.

Assessment-driven adaptive learning

  • Content is conditionally released based on performance against set established conditions within the LMS/VLE
  • Students are given access to more difficult content based on their performance and aptitude within the LMS/VLE
  • Data on learner profiles determine preference for content delivery modes and content adjusts on an individual student basis
  • Performance data from students struggling with concepts automatically trigger the availability of tutoring tips and additional learning resources
  • Recommended changes to student course selection or programme registration are provided based on correlation of student profile and performance data.

Feedback

Both assessment- and facilitator-driven adaptive learning approaches can be used to guide student progress by anticipating the content and resources a student needs in order to succeed. Feedback is an important element of the adaptive learning process, as is careful review and analysis of available student performance data. Take some time to review the reporting capabilities within your LMS/VLE, and consider how they can best be used to support an adaptive learning approach to student learning at your institution.

Do this icon

Remember, when you are teaching online you have access to valuable student data which can inform the way you design and develop learning assessments. Take some time to review grade and reporting features related to student assignments within your LMS/VLE, and look at how your students are performing individually, and overall. Use this data to inform your approach to advancing student success!


Foundations

Key terms

Learning analytics: Learning analytics is the collection and careful review of learner profile and performance data.

Personalised learning: Personalised learning is the individualised shaping of teaching and learning environments to meet the learning needs of students.

Adaptive learning: Adaptive learning is the computerised review and analysis of student profile and process data, which results in the immediate presentation of a more personalised learning environment.

Profile data: Student profile data includes demographic information, content delivery preference types, course selection preferences, success and failure patterns, and learning disability information.

Process data: Student process data includes assignment grades, completed activities or projects, and data related to course content area access.

Data mining: The review and statistical analysis of large data sets in order to categorise, find patterns, and evaluate identified correlations.

Useful links

Useful links