Learning analytics

Learning analytics is the measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimising learning and the environments in which it occurs.

Historically, some of the most common uses of learning analytics is the prediction of student academic success and identification of at-risk students in order to provide them with support. Analytics is not just limited to focusing on students. Data drawn from student interactions and online engagement can be used to improve teaching practices and resources. Additional goals of learning analytics include to:

support student agency and self-regulation
provide personalised and timely feedback to students
improve teaching practices through the use of empirical evidence on the success of pedagogical innovations
develop both student and educator awareness by supporting self-reflection

Methodologies View

There are four main methodologies for learning analytics: descriptive, diagnostic, predictive and prescriptive.

Descriptive analytics uses data aggregation and data mining to understand trends and evaluative metrics over time. It allows us to see what happened in a learning episode. The majority of statistics use falls into this category which is limited to past data and includes:
- student feedback gathered from student satisfaction and graduate surveys (ie SETU)
- analysis of data at all stages of the student lifecycle starting from admissions process, to student orientation, enrolments, pastoral care, study support, exams and graduations.
Diagnostic analytics is characterised by techniques such as drill-down, data discovery, data mining and correlations to examine data or content to answer the question ‐ “Why did it happen?” and includes:
- analysis of data to inform and uplift key performance indicators across the University (used to establish strategic programs at the University, Faculty or school level)
- analysis of patterns to design appropriate metrics
- equity access reporting and analysis of effective strategies to support students
- moodle metrics to improve student engagement.
Predictive analytics combines historical data to identify patterns in the data and applies statistical models and algorithms to capture relationships between various data sets to forecast trends. It allows us to predict what may happen and includes:
- development of dashboard to help predict student numbers and cohort mobility through programs to assist in identifying areas for improvement (ie student outreach dashboard).
Prescriptive analytics goes beyond the descriptive and predictive and recommends one or more choices by using a combination of machine learning, algorithms, business rules and computational modelling. This could include:
- a focus on unit/courses where small changes could have a big impact on improving student engagement, feedback and outcomes (course reviews)
- data visualisation via specific tools to provide program/degree level metrics on student enrolments, program stage, results and survey feedback to give teaching staff visual snapshots of students in their programs.

Strategies for using analytics View

Strategies for applying these methodologies within the context of Monash are further explained within this resource, including instructions of how to access analytics within learning technologies to optimise learning.

Platforms like Moodle, Panopto, and Echo360 gather information about student interactions, behaviours and activities that can be analysed to develop interventions for your students and improve learning resources.

Analytics can serve multiple purposes, including: indicating to the educator areas that need further instruction; identifying students who are struggling and need additional assistance; providing milestones and motivation for students to appreciate their own progress; allowing content to be customised to suit each individual learner’s needs; and many other benefits for both teacher and student.

The desired outcome of using analytics is to improve teaching approaches, content structure, formative and summative assessment, which leads to more effective teaching, better student experience, enhanced student understanding and better student grades.

Learning analytics in Moodle

Moodle has a vast amount of data that is presented in various formats including raw data logs and specific reports.

The table below lists the different types of Moodle reports and possible applications.

Type of guide	Contents	Application
Quick activity	Moodle site activity	Use to identify inactive participants who have not been on the Moodle site within a specific time period.
Alternative assessment info	Students requiring alternative assessment	Use to identify students who require alternative assessments.
Engagement analytics	Three indicators are weighted to calculate a student's level of risk	The weighting of the analytics can be adjusted according to the type of engagement that is the most important for your unit. An engagement analytics block can be added to the page to help quickly identify at risk students.
Logs	Selected activity by selected users within selected items for a selected period	Use this log to determine the student engagement with a specific activity. Low use may indicate refinement is required.
Live logs	The past hour of activity within the unit	Useful to measure students' activity immediately before or after a scheduled lesson.
Activity report	Number of views of each activity in the course, sorted by topic	This may give a general overview and comparison between activities to determine which type of activities are valued by students.
Unit participation	Selected actions by selected users for a selected period in relation to a selected activity	Tutors can choose their tutor group to monitor engagement for a specific activity, such as a quiz.The teacher may send all or selected users a message to encourage students to complete the quiz.
Activity completion	Completion of all activities for all users in the unit	This report can be sorted by group or name and downloaded in two different formats. This may require additional manipulation within a spreadsheet.
Statistics	Graph displayed based on unit, report type and time period	Use the graphs to quickly scan through the relevant student activity logs (views and posts) to identify any anomalies.

For additional information, see Moodle reports.

Education Performance Standards Framework

You can use the tabs on the left-hand side menu to navigate between the sections or click on the links below:
1. The How-to section provides you with instructions and/or strategies to implement in your teaching.
2. The Related technology section provides different polling tool options and links to related guides.
3. The Supporting your students section provides you with key strategies for creating a good learning experience and a list of resources to share.
4. The Related resources section provides you with additional resources.
Adesope, O. O., & Rud, A.G. editor. (2019). Contemporary Technologies in Education Maximizing Student Engagement, Motivation, and Learning (1st ed. 2019.).
Society for Learning Analytics Research. (2021, January 18). What is Learning Analytics? https://www.solaresearch.org/about/what-is-learning-analytics/.
Wise, A. (2019). Learning analytics, educational research, and pedagogical practices: Leveraging big data in powerful ways. In O. O. Adesope & A. G. Rud (Eds.), Contemporary technologies in education: Maximizing student engagement, motivation, and learning. New York: Palgrave Macmillan.

Your feedback matters

Let us know how we can improve this resource.

Analytics case study: Using analytics from Moodle lessons

Learn how lecturers in MKF1120 used Moodle lessons analytics to track students’ online activity and their performance to be able to offer appropriate and timely advice.

Using Moodle Data to Inform your Teaching

Explore how to retrieve meaningful data from Moodle and improve the learning experience.

The Centre for Learning Analytics at Monash

CoLAM is a world-leader in learning analytics – and a globally-renowned hub for educating students and professionals in this area. Gathering top expertise from around the world, we’re developing our field while making a real-world impact.

The Education Performance Standards identify the expectations of education practice at Monash – See the Education Performance Standards for more details.
Impact on student learning				Impact on educational knowledge		Impact on educational environment
Effective teaching and learning	Responsive program design	Student- centred orientation	Professional learning engagement	Pedagogical content knowledge	Education research performance	Education innovation	Education leadership
✓	✓	✓				✓
You could address these Practice Elements by providing evidence of how you: Improve teaching practices through the use of empirical evidence on the outcomes of pedagogical innovations Adopt evidence-led rationale for unit/ course design Provide targeted or personalised support to students through the use of data Empower students to reflect upon their learning through the use of learning analytics

Learning and Teaching: Teach HQ