LOAIHCFeb 8, 2022

Natural Language Proof Checking in Introduction to Proof Classes -- First Experiences with Diproche

arXiv:2202.08131v18 citations
Originality Synthesis-oriented
AI Analysis

This addresses the challenge of scalable feedback for students in introductory proof classes, though it is incremental as it applies an existing system to a new educational context.

The authors tackled the problem of providing immediate feedback on proof exercises in a beginner mathematics course by employing the Diproche natural language proof checker, resulting in its use with 228 students and assessment via questionnaires and solution analysis to guide future improvements.

We present and analyze the employment of the Diproche system, a natural language proof checker, within a one-semester mathematics beginners lecture with 228 participants. The system is used to check the students' solution attempts to proving exercises in Boolean set theory and elementary number theory and to give them immediate feedback. The benefits of the employment of the system are assessed via a questionnaire at the end of the semester and via analyzing the solution attempts of a subgroup of the students. Based on our results we develop approaches for future improvements.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes