@article{Rajagede_2021, title={Improving Automatic Essay Scoring for Indonesian Language using Simpler Model and Richer Feature}, volume={6}, url={https://kinetik.umm.ac.id/index.php/kinetik/article/view/1196}, DOI={10.22219/kinetik.v6i1.1196}, abstractNote={<p>Automatic essay scoring is a machine learning task where we create a model that can automatically assess student essay answers. Automated essay scoring will be instrumental when the answer assessment process is on a large scale so that manual correction by humans can cause several problems. In 2019, the Ukara dataset was released for automatic essay scoring in the Indonesian language. The best model that has been published using the dataset produces an F1-score of 0.821 using pre-trained fastText sentence embedding and the stacking model between the neural network and XGBoost. In this study, we propose to use a simpler classifier model using a single hidden layer neural network but using a richer feature, namely BERT sentence embedding. Pre-trained model BERT sentence embedding extracts more information from sentences but has a smaller file size than fastText pre-trained model. The best model we propose manages to get a higher F1-score than the previous models on the Ukara dataset, which is 0.829.</p>}, number={1}, journal={Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control}, author={Rajagede, Rian Adam}, year={2021}, month={Feb.}, pages={11-18} }