Ani Aghababyan

HART: the human affect recording tool

This paper evaluates the Human Affect Recording Tool (HART), a Computer Assisted Direct Observation (CADO) application that facilitates scientific sampling. HART enforces an established method for systematic direct observation in Educational Data Mining (EDM) research, the Baker Rodrigo Ocumpaugh Monitoring Protocol [25] [26]. This examination provides insight into the design of HART for rapid data collection for both formative classroom assessment and educational research. It also discusses the possible extension of these tools to other domains of affective computing and human computer interaction.

Learning Fractions by Splitting: Using Learning Analytics to Illuminate the Development of Mathematical Understanding

The struggle with fraction learning in kindergarten through Grade 12 in the United States is a persistent problem and one of the major stumbling blocks to succeeding in higher mathematics. Research into this problem has identified several areas where students commonly struggle with fractions. While there are many theories of fraction learning, none of the research on these theories employs samples large enough to test theories at scale or nuanced enough to demonstrate how learning unfolds over time during instructional activities based on these theories. The work reported here uses learning analytics methods with fine-grained log data from an online fraction game to unpack how splitting (i.e. partitioning a whole into equal-sized parts) impacts learning. Study 1 demonstrated that playing the game significantly improved students’ fraction understanding. In addition, a cluster analysis suggested that exploring splitting was beneficial. Study 2 replicated the learning results, and a cluster analysis showed that compared to early game play, later game play showed more optimal splitting strategies. In addition, in looking at the types of transitions that were possible between a student’s early cluster categorization and later cluster categorization, we found that some types of transitions were more beneficial for learning than others.

Nanogenetic learning analytics: illuminating student learning pathways in an online fraction game

A working understanding of fractions is critical to student success in high school and college math. Therefore, an understanding of the learning pathways that lead students to this working understanding is important for educators to provide optimal learning environments for their students. We propose the use of microgenetic analysis techniques including data mining and visualizations to inform our understanding of the process by which students learn fractions in an online game environment. These techniques help identify important variables and classification algorithms to group students by their learning trajectories.

Enhancing the Clustering of Student Performance Using the Variation in Confidence

While prior research has typically treated student self-confidence as a static measure, confidence is not identical in all situations. We study the degree to which confidence varies over time using entropy, investigating whether high variation in confidence is more characteristic of highly confident or highly uncertain students, using data from 118,000 students working within 8 courses within the LearnSmart adaptive platform. We find that more confident students are also more consistent in their confidence. Confident students were more likely to answer correctly but also more likely to be overconfident, making unexpected mistakes. Finally, we develop interpretable clusters of students based on their confidence entropy, degree of over/underconfidence, and related variables.

Cortical Activations During a Computer-Based Fraction Learning Game: Preliminary Results from a Pilot Study

Abstract Advances in educational neuroscience have made it possible for researchers to conduct studies that observe concurrent behavioral (i.e., task performance) and neural (i.e., brain activation) responses to naturalistic educational activities. Such studies are important because they help educators, clinicians, and researchers to better understand the etiology of both typical and atypical math processing. Because of its ease of use and robust tolerance of movement, functional near-infrared spectroscopy (fNIRS) provides a brain-imaging platform that is optimally suited for such studies. To that end, the focus of the current research is to use fNIRS to help better understand the neural signatures associated with real-world math learning activities. For example, the computer game “Refraction” was designed as a fun and engaging method to improve fraction knowledge in children. Data collected in previous studies have identified significant correlations between Refraction play and improvements in fraction knowledge. Here we provide the results of a pilot study that describes participants’ cortical activations in response to Refraction play. As hypothesized, Refraction play resulted in increases in parietal cortical activations at levels above those measured during spatial-specific activities. Moreover, our results were similar to another fNIRS study by Dresler et al. (J Neural Transm 116(12): 1689–1700, 2009), where children read Arabic numeral addition equations compared to written equations. Our results provide a valuable proof-of-concept for the use of Refraction within a large-scale fNIRS-based longitudinal study of fraction learning.