Learning analytics refers to the use of data generated during the learning process to support student guidance, assessment and the development of teaching. This data is derived from students’ activities (such as submitting assignments or navigating the course site) as well as log data produced by digital tools. Learning analytics can help to enhance learning, deepen our understanding of the learning process, and guide the development of teaching.
Learning analytics is typically divided into four categories, each with its own focus:
- Descriptive analytics: What has happened?
Descriptive analytics provides an overview of students’ activities and answers the question: What has happened during this course? Examples include monitoring student progress, counting assignment submissions and tracking participation in online discussions. This type of data helps in building a comprehensive understanding of the situation.
- Diagnostic analytics: Why did this happen?
Diagnostic analytics goes a step further by exploring the reasons behind an event or outcome. It can help teachers identify barriers to learning, such as overly challenging assignments or a lack of motivation. For example, diagnostic analytics might reveal that students are not reading the teacher’s feedback or that they have made an unusually high number of mistakes on a particular assignment. This information enables teachers to understand the underlying causes of specific student behaviours and pinpoint what is hindering their learning.
- Prescriptive analytics: What should be done in the future?
Prescriptive analytics supports decision-making and guides future actions. It can be used to send students automatic reminders about upcoming deadlines or to suggest specific progress pathways. Prescriptive analytics can help students maintain effective progress and enable teachers to provide timely instruction and guidance.
- Predictive analytics: What might happen?
Predictive analytics focuses on anticipating future outcomes. For example, it can estimate students’ likelihood of successfully completing a course or identify those at risk of falling behind. This approach relies on historical data and models that assess potential future behaviour and performance. Predictive analytics enables early intervention and the tailoring of support to students who may be falling behind.
Learning analytics is not only a resource for teachers. From students’ perspective, it is a useful tool for monitoring and improving their own learning. It enables students to track their progress, such as their course submissions, the time spent on the course site and contributions to online discussions. Prescriptive analytics can recommend which assignments to complete next and send reminders about upcoming deadlines, helping students to manage their time and make effective academic progress. Predictive analytics, on the other hand, can indicate the likelihood of completing the course at the current pace, motivating students to make adjustments early. When students learn to interpret and use this type of data, they can take an active role in steering their own learning process.
Leveraging learning analytics
Learning analytics can be applied in multiple ways to support learning, enhance student guidance, and improve course content and assessment processes. It makes different stages of the learning journey visible and enables timely and appropriate allocation of support measures. Analytics can be utilised, for example, in the following areas:
- Student progress: Analytics supports student progress by providing visibility that helps learners stay on schedule and remain motivated.
- Guidance and support: Through analytics, teachers can identify students who need additional assistance. Teachers can review reports that highlight the progress made by individual students or provide an overview of the entire group’s progress, enabling them to provide additional guidance and support.
- Developing course content: Analytics reveals how students engage with the course materials and activities. Teachers can see which tasks or resources have been actively used and which have received little attention. This helps them refine the structure and content of their courses to better meet students’ needs and learning styles.
- Assessment: Learning analytics supports assessment by providing data on student performance across assignments, exams and feedback. This enables teachers to make well-informed grading decisions and helps students understand their own level of achievement.
The use of learning analytics in teaching and guidance requires careful consideration and a responsible approach. It is important to remember that analytics does not tell the whole story. While it offers insights into student activity within a digital environment, it may not fully capture their competences, motivation or the quality of learning. Analytics must always be interpreted as part of a broader context.
Student motivation is a key factor. If analytics is used only to highlight shortcomings, it can be discouraging. It is important to also emphasise positive signals, such as progress and active participation, so that students perceive analytics as a tool for support, not judgement.
Students must be clearly informed about what data is collected, for what purpose, and how it will be used. Transparency builds trust and openness. Data protection principles must also be upheld. Learning analytics data must be stored and processed in accordance with assessment regulations and data protection practices. All data must be securely deleted when it is no longer needed.
Learning analytics tools
Digital learning environments, such as Moodle and Teams, continuously collect data on student activity. This data may include, for example, login frequency, assignment submission times, grades, participation in discussions, video viewing duration and the completion of exercises. Data is often also available from other digital tools that are used to support learning.
The log data generated by these tools provides an overall picture of the learning process. For example, teachers can see which course sections are most frequently accessed, when students begin to slow down, or which students are at risk of falling behind. At the same time, students can monitor their own progress and receive feedback that helps them plan their learning more effectively.
How do we identify what is essential from such a vast amount of data? How can we draw the right conclusions? Analysing extensive log data plays a key role in leveraging learning analytics for meaningful insights. Virtual learning environments can also offer visual reports and automated notifications that support decision-making for both teachers and students. When analytics is used in a pedagogically sound and transparent way, it can significantly enhance the learning experience and support personalised learning paths.
For more information about the learning analytics features available in tools used across Tampere Universities, please visit the Digital Toolkit: How to use learning analytics