Using Active Learning Methods to Strategically Select Essays for Automated Scoring

Abstract

Research on automated essay scoring has become increasing important because it serves as a method for evaluating students' written-responses at scale. Scalable methods for scoring written responses are needed as students migrate to online learning environments resulting in the need to evaluate large numbers of written-response assessments. The purpose of this study is to describe and evaluate three active learning methods than can be used to minimize the number of essays that must be scored by human raters while still providing the data needed to train a modern automated essay scoring system. The three active learning methods are the uncertainty-based, the topological-based, and the hybrid method. These three methods were used to select essays included as part of the Automated Student Assessment Prize competition that were then classified using a scoring model that was training with the bidirectional encoder representations from transformer language model. All three active learning methods produced strong results, with the topological-based method producing the most efficient classification. Growth rate accuracy was also evaluated. The active learning methods produced different levels of efficiency under different sample size allocations but, overall, all three methods were highly efficient and produced classifications that were similar to one another.

core technology behind and beyond ChatGPT

“…The use of language models for automated grading has also been combined with other methods to improve its performance. For instance, Firoozi et al (2022) integrated active learning methods to support automated essay scoring.…”

Neural Networks or Linguistic Features? - Comparing Different Machine-Learning Approaches for Automated Assessment of Text Quality Traits Among L1- and L2-Learners’ Argumentative Essays

“…However, further systematic experiments varying the amount of training data across ML approaches and prompts would be needed to quantify the relevance of training data size. Such investigations might also consider active learning approaches to minimize the required number of training examples (e.g.,Firoozi et al, 2023;Horbach & Palmer, 2016).…”