Automated Essay Grading

Using machine learning to assess human writing is both an interesting challenge and can potentially make quality education more accessable. Using a dataset of essays written for standardized tests, we trained different models using word features, per-essay statistics, and metrics of similarity and coherence between essays and documents. Within a single prompt, the models are able to make predictions that closely match those made by human graders. We also explored methods of giving more detailed feedback for essays, such as levels of coherence and technical correctness.