Evolutionary Clustering of Apprentices' Behavior in Online Learning Journals for Vocational Education
Learning journals are increasingly used in vocational education to foster self-regulated learning and reflective learning practices. However, for many apprentices, documenting their working experiences is a difficult task. Thus, providing personalized guidance could improve their learning experience. In this paper, we profile apprentices' evolving learning behavior in an online learning journal throughout their apprenticeship. We propose a novel multi-step clustering pipeline based on a pedagogical framework. The goal is to integrate different learning dimensions into a combined profile that captures changes in learning patterns over time. Specifically, the profiles are described in terms of help-seeking, consistency, regularity, effort, and quality of the activities performed in the learning journal. Our results on two populations of chef apprentices interacting with an online learning journal demonstrate that the proposed pipeline yields interpretable profiles that can be related to academic performance. The obtained profiles can be used as a basis for personalized interventions, with the ultimate goal of improving the apprentices' learning experience.
├── data
├── docs
│ ├── paper.pdf # paper submission
│ └── formal_notation.pdf # feature creation formulas
│
├── notebooks
├── sql
│ ├── semantic
│ ├── features
│ ├── cohort
│ └── results
└── src
├── etl
├── features
├── models
└── visualization