Automatic coding of students' writing via Contrastive Representation Learning in the Wasserstein space

TL;DR

This paper presents a novel contrastive learning approach in Wasserstein space for automating the scoring of students' biology lab reports, achieving human-level reliability and enabling large-scale qualitative analysis.

Contribution

It introduces a contrastive learning method in Wasserstein space for NLP scoring tasks, demonstrating high accuracy and reliability comparable to human raters.

Findings

Achieved high Quadratic Weighted Kappa scores in report scoring

Approached inter-rater reliability of human analysis

Enabled large-scale qualitative analysis in learning sciences

Abstract

Qualitative analysis of verbal data is of central importance in the learning sciences. It is labor-intensive and time-consuming, however, which limits the amount of data researchers can include in studies. This work is a step towards building a statistical machine learning (ML) method for achieving an automated support for qualitative analyses of students' writing, here specifically in score laboratory reports in introductory biology for sophistication of argumentation and reasoning. We start with a set of lab reports from an undergraduate biology course, scored by a four-level scheme that considers the complexity of argument structure, the scope of evidence, and the care and nuance of conclusions. Using this set of labeled data, we show that a popular natural language modeling processing pipeline, namely vector representation of words, a.k.a word embeddings, followed by Long Short Term Memory (LSTM) model for capturing language generation as a state-space model, is able to quantitatively capture the scoring, with a high Quadratic Weighted Kappa (QWK) prediction score, when trained in via a novel contrastive learning set-up. We show that the ML algorithm approached the inter-rater reliability of human analysis. Ultimately, we conclude, that machine learning (ML) for natural language processing (NLP) holds promise for assisting learning sciences researchers in conducting qualitative studies at much larger scales than is currently possible.