What We Do
At the Language and Educational Analytics Research Lab, we use data science to generate insights about language, learning, and education that support AI-driven theory, applications, research, and interventions.
Our work generally focuses on the use of natural language processing (NLP) techniques and the application of computational tools and machine learning algorithms to better understand language learning, student writing, and text comprehensibility as means to understand underlying cognitive functions. The LEAR lab works with collaborators to develop NLP tools for use by researchers, industry partners, and educational administrators. We also assess the application of NLP techniques like Large Language Models in educational settings (K-12 and adults) as a means of generating and testing student domain knowledge.
Find us on GitHub
Wherever possible, we accompany our publications with source code and supplementary resources. We also upload earlier versions of our work to a preprint database, so you can read them for free.
Datasets and Competitions
We produce large, public datasets. We also host competitions in which teams of scientists compete to model our data.
Software and Tutorials
We make tools that help researchers analyze language data. We also endeavour to share our computer code in a clearly explained and reproducible format.
We are a diverse and multidisciplinary group of researchers. Our team is awesome.