Unfolding students’ trajectories of computational thinking in a block-based programming environment: A machine learning approach

Project: Research project

Project Details


Despite much research into the educational benefits of block-based coding in both the affective and cognitive domains of student learning, it remains unclear how young learners, as novice programmers, develop their CT competence through coding activities. Although there have been studies on validating CT competence scales, little is known about how students’ learning processes and their patterns of CT development predict their learning outcomes. To address this gap, we propose a machine learning approach to analyzing students’ patterns of coding trajectories and their relationships with students’ CT competence across different pedagogical settings: individual learning, partially collaborative learning and collaborative learning. To delineate the coding trajectories, we will employ machine learning algorithms to transform computer codes submitted by students at different junctures of their learning processes into code embeddings, which are low-dimensional vectors capturing the syntactic as well as high-level semantic features of the computer codes.
Effective start/end date1/01/2331/05/25


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.