Explorance launches AI model to analyse NSS feedback
Tue, 7th Jul 2026 (Today)
Explorance has launched an artificial intelligence model designed to analyse open-ended feedback from the National Student Survey. It was developed with six UK universities.
The model sits within Explorance MLY, the company's qualitative analysis platform for higher education feedback. It is designed to sort large volumes of student comments into categories aligned with the National Student Survey, which universities widely use to assess the student experience.
It was built with input from the Universities of Bristol, Liverpool John Moores, Manchester, Nottingham, Strathclyde and Westminster. Using 1,200 data points, the system groups insights across 10 themes, including seven that map directly to NSS areas and three additional themes for institutions' own analysis.
Universities have long faced a practical challenge in handling the free-text element of student surveys. While numerical scores can be reviewed quickly, written comments often require manual coding and review, taking significant staff time and varying between teams.
The model is intended to automate that work by categorising comments, identifying sentiment, redacting sensitive material, highlighting recommendations and flagging critical issues. Explorance presents it as a way for survey and insight teams to move more quickly from raw comments to structured findings.
University input
The product was shaped through collaboration with university users already working with MLY on other student feedback exercises. This gave Explorance practical input on how institutions review comments and which categories matter most when analysing NSS responses.
Matt Claridge, Director of Sales, EMEA, at Explorance, linked the launch to the pressure universities face when annual survey data arrives and they need to interpret it quickly.
"With NSS 2026 results due out on 8 July, now is the ideal time for institutions to prepare to act quickly on the insights they receive. The NSS produces a large quantity of both quantitative and qualitative data, including thousands of open-text responses that provide rich insights into student perceptions. Traditionally, analysing this feedback is resource-intensive, time-consuming and prone to bias or inconsistency. MLY is purpose-built for turning large volumes of qualitative data into structured, actionable insights using advanced AI and machine learning models," Claridge said.
At the University of Nottingham, the model was presented as an extension of its previous use of MLY in other survey work. The university's strategy and insights team said the collaborative approach with other institutions was a significant part of the project.
"We began using MLY across other institutional surveys during 2025, so applying it to the NSS felt like a natural next step. One aspect we particularly valued was the collaborative nature of the process, not only with Explorance but also with other universities. Being able to contribute to a solution that could improve how institutions analyse student feedback across the sector was something we were very keen to support. Building this capability manually would require weeks of coding and analysis. MLY enables us to move from a highly manual process to one where insights can be generated much more quickly," said Ufuoma Elegbede, Analyst, Strategy and Insights, University of Nottingham.
Broader market
The launch reflects a wider move by education technology suppliers to apply artificial intelligence to administrative and analytical tasks in universities. In student survey analysis, the appeal lies less in replacing judgement than in reducing the burden of processing large numbers of comments before staff begin interpreting the findings.
Users at Liverpool John Moores University and the University of Strathclyde have reported reduced time and resource demands when reviewing NSS feedback through MLY, according to Explorance. The company said teams have used the platform's thematic analysis and summary tools to identify recommendations, areas for improvement and perceived strengths.
The Montreal-based business, founded in 2003, says it works with more than 1,000 organisations in over 50 countries. It counts universities among its core customers and says its products are used by 30% of the world's top universities.
MLY has already received external recognition in the education sector. In 2024, the platform won a Gold Award in the AI in Education category at the QS Reimagine Education Awards.
For universities, the significance of the new NSS-specific model will depend on whether it can shorten the gap between survey results arriving and decisions being taken on teaching, support and the wider student experience. The challenge will be deciding how far to trust automated classification when handling comments that are often nuanced, ambiguous or highly context-specific.