A survey on deep learning-based automated essay scoring and feedback generation

Abstract

Deep learning-based automated essay scoring (AES) models exhibit a remarkable ability to identify complex patterns within essays and then generate accurate score predictions in an end-to-end training fashion. However, these models face a critical limitation in explaining the specific patterns and features utilized for scoring, which are essential for interpreting the scores and offering constructive feedback to essay authors. Numerous studies have focused on essay scoring, with the aim of modeling prompt-specific, domain-adaptable, or trait-specific AES. While existing surveys on AES cover topics ranging from representation to scoring models, they primarily emphasize scoring models. This study addresses a crucial gap by encompassing research on feedback generation for essay assessment tasks. By delving into essay scoring and feedback generation, we synthesize several existing literature to provide readers with a comprehensive understanding of ongoing research in both deep learning-based essay scoring and automated feedback generation. We categorized the existing essay scoring studies into prompt-specific and cross-prompt AES models, noting that prompt-specific AES is extensively researched category. However, we have only come across a few studies concerning automated feedback generation, likely because of the limited availability of suitable datasets for researching such types of tasks. Moreover, this survey provides insights into approaches for essay representation, prevalent datasets, evaluation metrics, and challenges in automated essay scoring tasks. By shedding light on these aspects, our goal is to delineate the current landscape, identify key research directions, and pave the way for further advancements in automated essay assessment.