Adaptive Model for Computer-Assisted Assessment in Programming Skills

TL;DR

This paper presents an adaptive assessment model for programming skills that enhances evaluation accuracy by considering item relevance and student answers, demonstrated through simulations and real student experiments.

Contribution

Introduces a novel adaptive assessment methodology that improves objectiveness and relevance in programming skill evaluation, compatible with traditional testing formats.

Findings

Improves assessment accuracy over traditional methods

Enhances objectiveness by considering content relevance

Compatible with standard multiple choice test formats

Abstract

In this work, we show a methodology aimed to improve the quality of the assessment process for subjects related to basic programming. The method takes into account the relevance of the items and the students answers to follow different paths to improve the accuracy of the assessment process. We have developed numerical simulations and experiments with real students that demonstrate the advantages of this model when compared with traditional evaluation tools. This method improves the objectiveness and takes into account the relevance of the subject contents. We also demonstrate that the architecture of the algorithm is fully compatible with traditional multiple choice test formalisms. Our results can be directly used in computer-assisted tests for different subjects and disciplines, as well as used by the students as a self-evaluation tool with the objective of correcting their deficiencies in the learning process.