McMining: Automated Discovery of Misconceptions in Student Code

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Al-Hossami, Erfan, Bunescu, Razvan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912640336396288
author Al-Hossami, Erfan
Bunescu, Razvan
author_facet Al-Hossami, Erfan
Bunescu, Razvan
contents When learning to code, students often develop misconceptions about various programming language concepts. These can not only lead to bugs or inefficient code, but also slow down the learning of related concepts. In this paper, we introduce McMining, the task of mining programming misconceptions from samples of code from a student. To enable the training and evaluation of McMining systems, we develop an extensible benchmark dataset of misconceptions together with a large set of code samples where these misconceptions are manifested. We then introduce two LLM-based McMiner approaches and through extensive evaluations show that models from the Gemini, Claude, and GPT families are effective at discovering misconceptions in student code.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08827
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle McMining: Automated Discovery of Misconceptions in Student Code
Al-Hossami, Erfan
Bunescu, Razvan
Software Engineering
Artificial Intelligence
Computation and Language
Computers and Society
When learning to code, students often develop misconceptions about various programming language concepts. These can not only lead to bugs or inefficient code, but also slow down the learning of related concepts. In this paper, we introduce McMining, the task of mining programming misconceptions from samples of code from a student. To enable the training and evaluation of McMining systems, we develop an extensible benchmark dataset of misconceptions together with a large set of code samples where these misconceptions are manifested. We then introduce two LLM-based McMiner approaches and through extensive evaluations show that models from the Gemini, Claude, and GPT families are effective at discovering misconceptions in student code.
title McMining: Automated Discovery of Misconceptions in Student Code
topic Software Engineering
Artificial Intelligence
Computation and Language
Computers and Society
url https://arxiv.org/abs/2510.08827