Towards the Use of Slice-based Cohesion Metrics with Learning Analytics to Assess Programming Skills

TL;DR

This paper proposes using slice-based cohesion metrics to evaluate programming skills by analyzing the semantic relatedness of code segments during program construction, aiming to improve assessment in learning analytics.

Contribution

It introduces a novel approach to assess programming skills through cohesion metrics on variables, tailored for learning analytics and different student proficiency levels.

Findings

Cohesion metrics can identify programmers' trains of thought.

The approach differentiates skill levels based on semantic relatedness.

Potential for real-time assessment in educational settings.

Abstract

In programming education, it makes a difference whether you are dealing with beginners or advanced students. As our future students will become even more tech-savvy, it is necessary to assess programming skills appropriately and quickly to protect them from boredom and optimally support the learning process. In this work, we advocate for the use of slice-based cohesion metrics to assess the process of program construction in a learning analytics setting. We argue that semantically related parts during program construction are an essential part of programming skills. Therefore, we propose using cohesion metrics on the level of variables to identify programmers' trains of thought based on the cohesion of semantically related parts during program construction.