Student Performance Prediction from E-mail Assessments Using Tiny Neural Networks

Predicting student performance using e-mail assessments can help in early interventions to better assist students sooner, rather than later, in STEM courses. In this paper, we propose CorC-Net, a tiny artificial neural network (ANN) that operates on limited data comprised of features scored from student assessments based on writing e-mails. ANNs are typically built using large scale data sets to truly realize their full potential; however, tiny neural networks overcome this problem by utilizing smaller batches of data making them easier to train. COrC-Net uses scored e-mails for content, organization, and clarity and classifies how students will perform. Formative instructor feedback provided between the assessments implies that CorC-Net is a more logical fit to simulate the “learning” process when human reaction to feedback and corrective action is involved. This is true especially in sequential course assessment tasks. In this paper, we show that COrC-Net outperforms other multiclass classification algorithms like decision trees, support vector machines, Gaussian Naive Bayes, and K-nearest neighbors. CorC-Net's success in classifying student performance shows great potential in courses where longterm temporal assessment data is not available.