When text datasets are very large, manually coding line by line becomes impractical. As a result, researchers sometimes try to use machine learning algorithms to automatically code text data. One of the most popular algorithms is topic modeling. For a given text dataset, a topic model provides probability distributions of words for a set of…

More than ever in the past, researchers have access to broad, educationally relevant text data from sources such as literature databases (e.g., ERIC), an open-ended response from online courses/surveys, online discussion forums, digital essays, and social media. These advances in data availability can dramatically increase the possibilities for…

3D models derived from actual molecular structures have the potential to transform student learning in biology. We share findings related to our research questions: 1) what types of interactions with a protein folding kit promote specific learning objectives?, and 2) what features of the instructional environment (e.g., peer interactions, teacher…

The following report describes an assessment instrument called the Mathematics Performance and Cognition (MPAC) interview. The MPAC interview was designed to measure two outcomes of interest. It was designed to measure first and second graders' mathematics achievement in number, operations, and equality, and it was also designed to gather…

This report provides an overview of the development, implementation, and psychometric properties of a student mathematics interview designed to assess first- and second-grade student achievement and thinking processes. The student interview was conducted with 622 first- or second-grade students in 22 schools located in two public school districts…

This study characterized the use of research community partnerships (RCPs) to tailor evidence-based intervention, training, and implementation models for delivery across different childhood problems and service contexts using a survey completed by project principal investigators and community partners. To build on previous RCP research and to…

When validating assessment models built with data mining, generalization is typically tested at the student-level, where models are tested on new students. This approach, though, may fail to find cases where model performance suffers if other aspects of those cases relevant to prediction are not well represented. We explore this here by testing if…

On September 22, 2012, NSF announced its decision to fund a three-year project, "Models for Information Assurance Education and Outreach" (MIAEO). In the first year of grant operation, MIAEO has invited 18 high school students, two K-12 teachers, and two CSUB student assistants to conduct research explorations in the fields of…