This study examines the effectiveness of the Center for Civic Education's Project Citizen teacher professional development program and curriculum intervention in producing positive student learning outcomes that support civic engagement. Through Project Citizen, students identify and research a problem in their community, explore solutions,…

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…

This paper investigates two specific probabilistic biases which middle graders usually exhibit when reasoning about probability and randomness on assessment items. We discuss how students' reasoning about key probability concepts undergirds statistics literacy related to randomness, independence, and the likelihood of future events based on past…

MOOCs and online courses have notoriously high attrition [1]. One challenge is that it can be difficult to tell if students fail to complete because of disinterest or because of course difficulty. Utilizing a Deep Knowledge Tracing framework, we account for student engagement by including course interaction covariates. With these, we find that we…

This paper provides an alternative way of document representation by treating topic probabilities as a vector representation for words and representing a document as a combination of the word vectors. A comparison on summary data shows that this representation is more effective in document classification. [This paper was published in:…

The research shared in this conference paper report illustrates how an iterative process to item development that involves expert review and cognitive lab interviews with students can be used to collect evidence of validity for assessment items. Analysis of students' reasoning was also used to expand a model for identifying conceptions and…

In this paper, we investigate two purported problems with Bayesian Knowledge Tracing (BKT), a popular statistical model of student learning: "identifiability" and "semantic model degeneracy." In 2007, Beck and Chang stated that BKT is susceptible to an "identifiability problem"--various models with different…

Understanding students' misconceptions and how they change is an essential part of supporting students in their science learning. This paper presents results from distractor-driven multiple-choice assessments that target students' misconceptions about energy. Over 20,000 elementary, middle and high school students from across the U.S. participated…

Energy plays a central role in our society, so it is essential that all citizens understand what energy is and how it moves and changes form. However, research has shown that students of all ages have difficulty understanding these abstract concepts. This paper presents a summary of elementary, middle, and high school students' understanding of…

Can student performance on computer-based tests (CBT) and paper-and-pencil tests (PPT) be considered equivalent measures of student knowledge? States and school districts are grappling with this question, and although studies addressing this question are growing, additional research is needed. We report on the performance of students who took…

This study used propensity score techniques on data from the National Longitudinal Transition Study-2 to assess the causal relationship between speech and behavior-based support services and rates of social communication among high school students with Autism Spectrum Disorder (ASD). Findings indicate that receptive language problems were…

Using data from waves 1 through 5 of the National Longitudinal Transition Study-2, this study used propensity score techniques to assess the relationships between general education inclusion and college enrollment rates among youth with Autism Spectrum Disorder (ASD). Data show that 2- or 4-year college enrollment rates were significantly higher…