This paper proposes an online testing and analysis system for studying students’ Creative Problem-Solving (CPS) ability in sciences. Using an open-ended essay-question-type test, students are asked to express their idea and imagine how to solve problems better. Based on previous works, we utilize an automated scorer for evaluating students’ CPS ability. This system serves as a real-time (self-)...

Automated scoring of open-ended student responses has the potential to significantly reduce human grader effort. Recent advances in automated leverage textual representations from pre-trained language models like BERT. Existing approaches train a separate model for each item/question, suitable scenarios essay where items can be different one another. However, these have two limitations: 1) they...

Existing approaches for automated essay scoring and document representation learning typically rely on discourse parsers to incorporate structure into text representation. However, the performance of is not always adequate, especially when they are used noisy texts, such as student essays. In this paper, we propose an unsupervised pre-training approach capture essays in terms coherence cohesion...

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 predic...

In automated essay scoring (AES), scores are automatically assigned to essays as an alternative grading by humans. Traditional AES typically relies on handcrafted features, whereas recent studies have proposed models based deep neural networks obviate the need for feature engineering. Those generally require training a large dataset of graded essays. However, grades in such known be biased owin...

We have set out to create a system that gives essay feedback by identifying stronger and weaker parts of a given essay. In order to do this, we have created a two step model: the first step uses an LSTM to turn a chunk of an essay into an encoding vector. The second step uses a feed forward network to assign a score to an encoding. We believe that if the feed forward network is able to predict ...