In this study, we investigated the validity of a stealth assessment of physics understanding in an educational game, as well as the effectiveness of different game-level delivery methods and various in-game supports on learning. Using a game called "Physics Playground," we randomly assigned 263 ninth- to eleventh-grade students into four…

In-game learning supports aim to help students solve game levels (i.e., game-related supports), and connect to underlying content (i.e., content-related and hybrid supports). Students with different levels of prior knowledge may have different needs for in-game supports. In this study, we designed a 2D physics game with game-related,…

Persistence is an important part of student success--both in and out of school. To enhance persistence, we first need to assess it accurately. Digital games can be used as vehicles for measuring and enhancing persistence. The purpose of this study is to test the effects of (a) game-level characteristics (i.e., game mechanics and conceptual…

Persistence is an important part of student success--both in and out of school. To enhance persistence, we first need to assess it accurately. Digital games can be used as vehicles for measuring and enhancing persistence. The purpose of this study is to test the effects of (a) game-level characteristics (i.e., game mechanics and conceptual…

We examined the use and effectiveness of an incentive system--one of the five elements of a theory-based motivational architecture in educational games that we proposed--in a computer-based physics game on students' learning and performance. The incentive system's purpose was to motivate students to access learning supports designed to facilitate…

Identifying struggling students in real-time provides a virtual learning environment with an opportunity to intervene meaningfully with supports aimed at improving student learning and engagement. In this paper, we present a detailed analysis of quit prediction modeling in students playing a learning game called Physics Playground. From the…

Educational games have become hugely popular, and educational data mining has been used to predict student performance in the context of these games. However, models built on student behavior in educational games rarely differentiate between the types of problem solving that students employ and fail to address how efficacious student problem…

Increased attention to the relationships between affect and learning has led to the development of machine-learned models that are able to identify students' affective states in computerized learning environments. Data for these affect detectors have been collected from multiple modalities including physical sensors, dialogue logs, and logs of…