Jisc learning analytics for wellbeing, and what it means for student support evidence
Updated Apr 08, 2026
Learning analytics can show when a student is drifting before an annual survey ever captures the problem. That is why Jisc’s March 2026 Newcastle case study matters: it shows how engagement data can support earlier wellbeing conversations, and why universities still need stronger evidence behind each intervention. On 12 March 2026, Jisc published a podcast case study, Beyond the Technology: using Jisc learning analytics to support wellbeing, showing how Newcastle University's wellbeing team uses learning analytics to identify issues earlier and shape support conversations. For Student Experience teams, PVCs, and quality professionals, the practical takeaway is clear: earlier signals only help if institutions can turn them into trustworthy, well-governed action.
What has changed in Jisc learning analytics for wellbeing
This is not a new regulatory requirement or a survey methodology change. The shift is that Jisc now frames learning analytics, through a current Newcastle University example, as a practical wellbeing and student support tool, not only a retention or compliance tool. The podcast summary says the approach uses engagement and attendance data, including virtual learning environment activity and in-person participation, to help wellbeing staff identify students who may be struggling, guide conversations, and make better-informed decisions about interventions. For institutions, that matters because learning analytics is being positioned as a frontline support input, not just a reporting layer.
"This episode looks at how Jisc learning analytics empowers wellbeing teams at Newcastle University to identify issues early and improve student support."
The supporting Jisc learning analytics page makes the wider scope clear. Jisc describes a single service that combines learning analytics, attendance monitoring, and case management, with configurable dashboards, module-level views, notifications, and a student web app. It says the service is intended to help universities improve student success, support wellbeing, and meet regulatory demands. In other words, this is a live UK sector offer, not a one-off local pilot. That makes the Newcastle example more useful to institutions assessing whether this kind of workflow can scale beyond a single team.
Jisc's code of practice for learning analytics is also relevant background. It says institutions should define who is responsible for data collection, anonymisation, analytics, interventions, and data stewardship, and that student representatives should be consulted on objectives, design, rollout, and monitoring. It also stresses transparency about data sources, metrics, access, and the purpose of interventions. That governance context matters because the Newcastle example is not just about having more data. It is about using that data in a way students and staff can understand and trust, which makes early intervention more defensible.
What this means for institutions
The first implication is operational. If universities want to use learning analytics for wellbeing, they need more than a dashboard. They need a clear service model that defines who reviews alerts, what counts as a meaningful change in engagement, when a case should move from observation to intervention, and how decisions are recorded. That is the same institutional discipline Jisc highlighted in its earlier post on building a business case for learning analytics: analytics only become credible when responsibilities, workflows, and review points are explicit. The benefit is faster, more consistent action when a concern appears.
The second implication is evidential. Engagement data can show that something has changed, but not always why. A drop in attendance or online activity might reflect workload pressure, poor assessment design, disability-related barriers, financial stress, or a student deliberately disengaging from a service they do not trust. Institutions should therefore treat learning analytics as one part of a wider student experience evidence base alongside internal student experience surveys, wellbeing check-ins, rep systems, and open-text comment analysis. Recent examples on this site, including Newcastle Experience Survey 2026 and King's Wellbeing Survey, point in the same direction: joined-up student support depends on joined-up evidence. That wider view helps teams distinguish between a welfare issue, a teaching issue, and a service-design issue before they intervene.
The third implication is communication. If a university is monitoring engagement for support purposes, students need to know what data is in scope, who can see it, how it will be interpreted, and what kinds of interventions may follow. That is especially important where wellbeing and safeguarding are involved. Jisc's code is clear that analytics should be explained in context, access should be restricted to those with a legitimate need, and interventions should be auditable and reviewed. For quality and student experience leaders, that makes learning analytics partly a governance question and partly a student trust question. If students do not understand the purpose, the same system designed to help can weaken confidence instead.
How student feedback analysis connects
At Student Voice AI, we see the strongest institutional practice when behavioural signals and student voice are read together. Learning analytics may show that engagement has dropped in a module, service, or cohort. Open-text feedback helps explain whether students are talking about unclear expectations, inaccessible support, assessment pressure, poor communication, or a broader sense of belonging. Without that qualitative layer, teams risk acting on a pattern without understanding the student experience behind it. The benefit of combining both sources is that support teams can respond with more precision.
That is why comment analysis still matters here. Universities already collect free-text evidence through NSS, PTES, PRES, module evaluations, service surveys, and local pulse work. A defensible workflow such as our NSS open-text analysis methodology helps teams compare those comments systematically, identify where support issues are recurring, and check whether interventions are changing what students actually report. Learning analytics can tell you which students or groups may need attention; student feedback analysis helps show what kind of response is likely to help. If you need a reproducible way to connect support-related comments across surveys and services, explore Student Voice Analytics.
FAQ
Q: What should institutions do now if they want to use learning analytics for wellbeing more credibly?
A: Start by mapping the student support workflow around the data, not just the data itself. Agree which engagement indicators are reviewed, who can access them, when an alert becomes an intervention, how student consent and transparency are handled, and which mid-module feedback routes will be used to review whether the intervention actually helped. That keeps the focus on support rather than surveillance.
Q: What is the timeline and scope of this Jisc development?
A: The primary source was published by Jisc on 12 March 2026 and focuses on Newcastle University's use of Jisc learning analytics for wellbeing support. The wider service is aimed at UK universities and colleges using Jisc learning analytics. This is a sector practice example rather than a mandatory regulatory change.
Q: What is the broader implication for student voice?
A: The broader implication is that student voice should not be treated as separate from other student experience signals. Universities are more likely to act well, and more fairly, when they combine engagement data with qualitative feedback instead of treating either source as sufficient on its own.
References
[Jisc]: "Beyond the Technology: using Jisc learning analytics to support wellbeing" Published: 2026-03-12
[Jisc]: "Learning analytics" Published: not stated
[Jisc]: "Code of practice for learning analytics" Published: not stated
Request a walkthrough
Book a free Student Voice Analytics demo
See all-comment coverage, sector benchmarks, and reporting designed for OfS quality and NSS requirements.
- All-comment coverage with HE-tuned taxonomy and sentiment.
- Versioned outputs with TEF-ready reporting.
- Benchmarks and BI-ready exports for boards and Senate.
UK-hosted · No public LLM APIs · Same-day turnaround