Agentic education · Learning science

Actionable companion · Accessibility & inclusion

Learning with agency: Clustering analysis of factors affecting academic career of university students with dyslexia in Italy

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Secondary school, Higher education. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

This study was designed to explore learning experiences of university students with dyslexia and factors that could contribute to their success in the university career. Although, great efforts have been made to diagnose dyslexia and to mitigate its effects at primary and secondary school, little has been done at the university level in particular in the Italian context. Indeed in the university context, the availability and possibility to use of support tools, that enable the student to achieve educational success, is still not sufficiently adequate. In this paper we used bivariate association tests and cluster analysis, in order to identify the most suitable compensatory tools and support strategies that can facilitate the students’ performance in higher education. The data were obtained through the voluntary participation of Italian students, enrolled in a bachelor degree course, with certified diagnosis of dyslexia. Six groups of students were identified from the cluster analysis, defining specific support tools and learning strategies for each group. Furthermore, through the creation of these six groups, it was possible to describe “profiles” that highlight the risk factors (late diagnosis) and-or protection factors (such as associations, support from friends and family) in analyzing the academic career of students with dyslexia. Therefore, starting from these data, through artificial intelligence it will be possible to identify and suggest study methodologies and create specific support tools for each student that can enable her/him to achieve educational success in her/his academic career.

What kind of evidence is this?

Supporting AI learning science · Design requires full-text appraisal

Stage: Secondary school; Higher education. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Study methods · source passage

We here adopted an agglomerative algorithm in order to apply a cluster analysis, which is a multivariate statistical tool aimed at grouping a set of units in such a way that units in the same group (called as a cluster) are more similar to each other than to those in other groups (clusters). This method is the most common type of hierarchical clustering used to group units in clusters based on their similarity since it is suitable for constructing and identifying typological groupings that can be both distinct from each other and internally homogeneous34. In our study, the units of analysis were students who participated in the survey. Agglomerative hierarchical clustering techniques proceed by a series of successive mergers. It starts with the individual units, thus there are initially as many clusters as units. The most similar units are first grouped, and these initial groups are merged according to their similarities. Eventually, as the similarities decrease, all subgroups are fused into a single cluster. Concerning the measure of similarity, we used the Gower distance35. The Gower distance is a metric that measures the dissimilarity of two items with mixed numeric and non-numeric data. Gower distance is also called Gower dissimilarity. This is the most popular distance for mixed-type variables; it is appealing because ranges between 0 and 1, being an average of the scaled distances calculated variable by variable. The Gower’s distance can be defined as the complement to one of the Gower’s similarity coefficient: \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d_{G,ij}=1-s_{G,ij}=\frac{\sum _{t=1}^{p}\delta _{ijt}d_{ijt}}{\sum _{t=1}^{p}\delta _{ijt}}.$$\end{document}dG,ij=1-sG,ij=∑t=1pδijtdijt∑t=1pδijt.

Design the system before the pilot

Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.

  • Co-design accommodations with learners and specialists. Check access and error burden across groups without inferring subgroup effectiveness from small or unreported samples.

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Ask learners to attempt a problem unaided, compare an agent hint, explain a revision and verify the final reasoning against a trusted source. Make the permitted use explicit for each assignment. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Measure unaided transfer and delayed retention, calibration of confidence and the ability to identify an incorrect AI explanation. Record whether help-seeking becomes answer copying. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Ilaria Benedetti; Marcella Barone; Valentina Panetti; Juri Taborri; Tony Urbani; Andrea Zingoni; Giuseppe Calabrò. Clustering analysis of factors affecting academic career of university students with dyslexia in Italy. Scientific Reports (2022-05-30). https://doi.org/10.1038/s41598-022-12985-w

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.