EssayGAN: Essay Data Augmentation Based on Generative Adversarial Networks for Automated Essay Scoring
importance 4/10
ai assisted
Topic Modeling education technology stage: research
Problem
Deep-learning automated essay scoring systems are limited by the scarcity of large training datasets of manually rated essays.
Why it matters
Manual essay grading is burdensome in large-scale testing and e-learning environments.
What the AI did
EssayGAN uses multiple score-specific generators and one discriminator to synthesize essays rated with target scores, augmenting training data for automated essay scoring.
Results
not stated in source
Impact
Proposes a data-augmentation approach for essay scoring; measured improvement not stated in source.
Record
| Venue | Applied Sciences |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Yo-Han Park, Yong‐Seok Choi, Cheon-Young Park, Kong-Joo Lee |
| Citations | 17 (OpenAlex, at import time) |
| References | 18 |
| Model or method | EssayGAN (generative adversarial network, sentence-based generation) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/app12125803 |
| Open access | gold |
| Keywords | GAN, automated essay scoring, data augmentation, text generation, e-learning |
Importance rating
4
real but narrower advance
Abstract states automated essay scoring relieves human grading burden in large-scale testing and e-learning; a real but domain-specific efficiency advance.