Main content

Home

Menu

View
Wiki Version:
https://educationaldatamining.org/edm2019/proceedings/ ## Background ## This paper improves the training/testing process of AES in our previous study (Boulanger & Kumar, 2018). It uses exactly the same dataset and set of writing features. It demonstrates that the performance reported in the previous study is yet inflated due to the shuffling of essays in the training, validation, and testing sets. In fact, when averaging the model's performance over five different shufflings, we get a QWK of only 0.63. Moreover, this paper is one of the first to predict rubric scores on ASAP datasets. It tests the performance of several deep learning architectures against a baseline model (majority classifier).
OSF does not support the use of Internet Explorer. For optimal performance, please switch to another browser.
Accept
This website relies on cookies to help provide a better user experience. By clicking Accept or continuing to use the site, you agree. For more information, see our Privacy Policy and information on cookie use.
Accept
×

Start managing your projects on the OSF today.

Free and easy to use, the Open Science Framework supports the entire research lifecycle: planning, execution, reporting, archiving, and discovery.

Copyright © 2011-2024 Center for Open Science | Terms of Use | Privacy Policy | Status | API
TOP Guidelines | Reproducibility Project: Psychology | Reproducibility Project: Cancer Biology