# Automating Program Structure Classification

arXiv: https://arxiv.org/abs/2101.10087 · HTML: https://mlsanity.com/paper/2101.10087/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 37 references that are in the map.
- First posted on arXiv 15 Jan 2021.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks](https://mlsanity.com/paper/1503.00075/) (2015)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [Getafix: Learning to Fix Bugs Automatically](https://mlsanity.com/paper/1902.06111/) (2019)
- [Automated Clustering and Program Repair for Introductory Programming Assignments](https://mlsanity.com/paper/1603.03165/) (2016)
- [Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference](https://mlsanity.com/paper/1809.01357/) (2018)
- [Targeted Example Generation for Compilation Errors](https://mlsanity.com/paper/1909.00769/) (2019)
- [Generative Grading: Near Human-level Accuracy for Automated Feedback on Richly Structured Problems](https://mlsanity.com/paper/1905.09916/) (2019)

## Built on by (most cited first, 1 of 1)

- [Adaptive Scaffolding in Block-Based Programming via Synthesizing New Tasks as Pop Quizzes](https://mlsanity.com/paper/2303.16359/) (2023)

## Abstract (arXiv)

When students write programs, their program structure provides insight into their learning process. However, analyzing program structure by hand is time-consuming, and teachers need better tools for computer-assisted exploration of student solutions. As a first step towards an education-oriented program analysis toolkit, we show how supervised machine learning methods can automatically classify student programs into a predetermined set of high-level structures. We evaluate two models on classifying student solutions to the Rainfall problem: a nearest-neighbors classifier using syntax tree edit distance and a recurrent neural network. We demonstrate that these models can achieve 91% classification accuracy when trained on 108 programs. We further explore the generality, trade-offs, and failure cases of each model.