The GBA design is grounded in recent research in game-based learning, evidence-centered design (ECD), and education data mining (EDM). We use a game-based learning experience to implement a version of ECD's task/content/evidence model into the game design. We then collect patterns of click-stream data, as in EDM, to develop records of in-game player interaction that can be used as evidence for learning. Here we briefly review some of the core research ideas that led to our GBA design. Video games and learning. Kurt Squire asserts that "games differ from simulations in that they give roles, goals, and agency", and use "transgressive play" (Salen & Zimmerman, 2004) to "elicit fantasies" (Squire, 2011, p. 29). A key aspect of effective game design is the integration of data channels that inform both play and design. Gee (2005) highlights how good video games include just-in-time information (scaffolding) and cycles of expertise. Good games include formative assessment cycles that foster ongoing feedback and customize player difficulty levels (Shute, 2011). In order to maintain this immersive context for learning, good games consist of ongoing assessment balanced with engaging mechanics and narrative (Squire, 2006). Good games are not only scaffolded, engaging designed experiences (Squire, 2006), they also hold the power to improve learning. Situated learning theory suggests that learning exists in situ, inseparable from environment or context (Brown & Collins, 1989). Virtual game worlds have been shown to provide a powerful environment for learning, supporting apprenticeship and collective higher-order thinking skills

No abstract

No abstract

Abstract.Cognitive scientists and assessment developers have long been concerned with creating comprehensive, authentic measures-especially which elicit evidence of proficiency on one or more constructs under conditions of focus and engagement of test takers reflecting their true performance level. This challenge is particularly arduous for complex constructs, including 21 st century skills, that can be highly contextualized and involve the interplay of multiple skills. The current work describes the recent development and evaluation of a game-based assessment on argumentation skills, called Mars Generation One (MGO). Our results show that the in-game process data can substantially improve the measurement of argumentation compared to non-interactive multiplechoice tests. Lastly, students' show high levels of engagement and improve their argumentation skills during gameplay. Keywords:Game-based assessment · ECgD · Argumentation IntroductionThere are many indicators that large assessment systems (e.g., PARCC) are increasingly interested in and poised to adopt cognitively-based assessments [1], entailing assessing and reporting on the cognitive processes involved in solving and reasoning about a problem [2]. An important driver is a gradual shift in focus for curriculum and assessment standards from declarative knowledge to the interplay of practices and contexts (e.g., NGSS) and an increased interest in more complex 21 st century skills. The advances in technology and the way people interact with it opens up the possibility to create safe, interactive, and engaging learning and assessment environments to simulate and manipulate otherwise time-, space-, or cost-prohibitive objects and interactions. It also opens up the possibility to record those interactions more directly and continuously as a basis for making inferences about performance. The development of scenario-based tasks and educational simulations are important developments in this direction. Game-based assessment (GBA) is another, taking particular advantage of the interactivity and engagement games are built around.

Digital games can be potent problem solving environments which afford discovery learning through thoughtful exploration [1, 2]. As such, game microworlds facilitate self-regulated learning through sandbox elements in which students have agency in individualizing their pathways of interaction [3]. These agencydriven environments can support learning via individual discovery of problem space constraints and solutions, particularly through boundary testing and productive failure [cf. 4]. Thus, modeling of user interaction in digital learning games can provide considerable insight into emergent trajectories of discovery-based progression, in which equally engaged players may interact differently with the system. To this end, this research leverages educational data mining (EDM) [5] to investigate organic player trajectories of thoughtful exploration (around boundary testing and productive failure) in a learning gamespace. We align behavioral coding with log file data to automatically detect sequences of thoughtful exploration (TE) in play. Results include a robust predictive model of event-stream TE, with multiple trajectories of emergent student behavior-offering insight into organic learning pathways through the game-based problem space, and informing iterative design in optimization of user experience and student engagement.