Key Skills

Job Description

Research how behavioural learning data can be used to personalise content sequencing in an open-source learning platform. You will investigate whether interaction patterns can reveal learning progress and support adaptive learning without relying on formal assessments. In doing so, you contribute to the design of more effective and personalised learning experiences. This master’s thesis is part of the ‘Operation: Human Intelligence’ project. In this project, you will work alongside other IT students to build the learning platform of the future: open source, European and AI-assisted. You will help learners move forward with a platform that adapts to different ways of learning. An open-source learning platform is being developed for technical education. It will structure learning content as a hierarchy of Blocks, Modules, and Learning Paths, targeting IT professionals working through structured curricula at their own pace. At the time of writing this proposal, the platform is in the design phase. In most online learning systems each learner is expected to follow the same sequence, regardless of how they actually interact with the content. In practice, learners behave very differently: some skip sections they find too easy, some revisit the same block multiple times, some stall at specific points and never return. The platform currently has no mechanism to observe these patterns and respond to them. This is a missed opportunity. Behavioural signals (time-on-task, error frequency, revisit rate, skip patterns) are already implicit in how learners move through the platform. If those signals could be interpreted meaningfully, the platform could present content in a sequence better suited to each individual learner, rather than forcing everyone through the same fixed order. The challenge is not purely technical. Defining what “better” means in this context is genuinely hard. Learning outcomes are difficult to operationalise in a platform without formal examinations. There is also a cold-start problem: a system that relies on observed behaviour has nothing to work with for new learners. And behavioural tracking raises GDPR obligations (consent, data minimisation, purpose limitation) that constrain what can be collected and how long it can be kept. This thesis is part of the Operation: Human Intelligence project. Within this project, you will collaborate with other IT students to build the learning platform of the future: open source, European, and AI-assisted. The platform is designed to help learners progress more effectively by adapting to different ways of learning. The Assignment Learning analytics and knowledge tracing offer established ways to infer learning state from digital trace data. [1] In assessment-heavy systems (e.g., MOOCs and intelligent tutoring systems), models such as Bayesian Knowledge Tracing (BKT) and Deep Knowledge Tracing (DKT) estimate latent mastery mainly from sequences of scored item responses. [2] Our new e-learning platform lacks a formal assessment layer: the primary signals available are navigation patterns, time-on-task, and voluntary revisit behaviour. Research on clickstream data suggests these traces can be informative, but also partial and noisy, requiring careful interpretation and validation. [1] This project explores whether assessment-free behavioural signals can support content sequencing that improves learning outcomes (e.g., retention or transfer measured outside the platform). What constraints does this impose on system design (which signals to log, how to model uncertainty), and how can impact be evaluated when a classical control group is not feasible? 1: https://pmc.ncbi.nlm.nih.gov/articles/PMC9206225/ 2: https://link.springer.com/content/pdf/10.3758/s13428-022-01844-1.pdf About Info Support Info Support specializes in custom software, data/AI solutions, management, and training and is active in the Finance, Industry, Agriculture, Food & Retail, Mobility & Public, and Healthcare sectors. We provide solid and innovative solutions for complex and critical software issues. Our headquarters are located in Veenendaal (NL) and Mechelen (BE). At present, approximately 500 employees are employed by Info Support. Info Support’s working method is characterized by a number of core values: solidity, integrity, craftsmanship, and passion. These core values are intertwined in our work and the way we interact with each other. To ensure that all employees are always up to date with the latest developments, Info Support has an in-house IT Academy that eagerly satisfies the hunger for more or different knowledge and skills. B2 language proficiency in Dutch is required.

Core Responsibilities

Research how learner behaviour data, such as navigation patterns, time-on-task, errors, revisits, and skips, can be used to infer learning progress and personalise content sequencing without formal assessments. Collaborate with IT students on an open-source learning platform and investigate system design constraints and ways to evaluate learning impact.

Requirements

This is a master's thesis internship focused on learning analytics and adaptive content sequencing in an open-source learning platform. Dutch proficiency at B2 level is required; no specific prior work experience is stated.