@article {358, title = {Understanding Hybrid-MOOC Effectiveness with a Collective Socio-Behavioral Model}, journal = {Journal of Educational Data Mining (JEDM)}, volume = {11}, year = {2019}, pages = {42--77}, abstract = {Online courses for high school students promise the opportunity to bring critical education to youth most at need, bridging gaps which may exist in brick-and-mortar institutions. In this work, we investigate a hybrid Massive Open Online Course for high schoolers which includes an in-person coaching component. We address the efficacy of these courses and the contribution of in-person coaching. We first analyze features of student behavior and their effect on post-test performance and then propose a novel probabilistic model for inferring student success on an AP exam post-test. Our proposed model exploits relationships between students to collectively infer student success. When these relationships are not directly observed, we formulate latent constructs to capture social dynamics of learning. By collectively inferring student success as a function of both unobserved individual characteristics and relational dynamics, we improve predictive performance by up to 6.8\% over an SVM model with only observable features. We propose this general socio-behavioral modeling framework as a flexible approach for including unobserved aspects of learning in meaningful ways, in order to better understand and infer student success.}, doi = {10.5281/zenodo.3594773}, url = {https://doi.org/10.5281/zenodo.3594773}, author = {Sabina Tomkins and Lise Getoor} } @conference {tomkins:edm16, title = {Predicting Post-Test Performance from Online Student Behavior: A High School MOOC Case Study}, booktitle = {EDM}, year = {2016}, abstract = {

With the success and proliferation of Massive Open Online Courses (MOOCs) for college curricula, there is demand for adapting this modern mode of education for high school courses. Online and open courses have the potential to fill a much needed gap in high school curricula, especially in fields such as computer science, where there is shortage of trained teachers nationwide. In this paper, we analyze student post-test performance to determine the success of a high school computer science MOOC. We empirically characterize student success by using students{\textquoteright} performance on the Advanced Placement (AP) exam, which we treat as a post test. This post-test performance is more indicative of long-term learning than course performance, and allows us to model the extent to which students have internalized course material. Additionally, we analyze and compare the performance of a subset of students who received in-person coaching at their high school, to those students who took the course independently. This comparison provides better understanding of the role of a teacher in a student{\textquoteright}s learning. We build a predictive machine learning model, and use it to identify the key factors contributing to the success of online high school courses. Our analysis demonstrates that high schoolers can thrive in MOOCs.

}, keywords = {high school MOOCs, online education, student learning}, author = {Sabina Tomkins and Arti Ramesh and Lise Getoor} }