Ryan S. Baker
YOU?
Author Swipe
View article: Data Plus Theory Equals Codebook: Leveraging LLMs for Human-AI Codebook Development
Data Plus Theory Equals Codebook: Leveraging LLMs for Human-AI Codebook Development Open
Recent research has explored the use of Large Language Models (LLMs) to develop qualitative codebooks, mainly for inductive work with large datasets, where manual review is impractical. Although these efforts show promise, they often negle…
View article: The Coming but Uneven Storm
The Coming but Uneven Storm Open
This article investigates the state of AI regulations from diverse geopolitical contexts including the European Union, the United States, China, and several African nations, and their implications for learning analytics (LA) and AI researc…
View article: The effect of football (soccer) heading on gross and fine motor control in women
The effect of football (soccer) heading on gross and fine motor control in women Open
Introduction Heading is an integral component of football, but concerns remain about its impact on brain health. This study examines the acute effects of heading on gross and fine motor control as a measure of the motor-cognitive function …
View article: Keeping Students in their Zone of Proximal Development: A Machine Learning Approach for Intelligent Tutoring Systems
Keeping Students in their Zone of Proximal Development: A Machine Learning Approach for Intelligent Tutoring Systems Open
Students benefit from working on content that is challenging without being too difficult. However, even in adaptive learning systems, ensuring that the content meets these criteria for all students can be complex. To complement placement t…
View article: Starting Seatwork Earlier as a Valid Measure of Student Engagement
Starting Seatwork Earlier as a Valid Measure of Student Engagement Open
Prior work has developed a range of automated measures ("detectors") of student self-regulation and engagement from student log data. These measures have been successfully used to make discoveries about student learning. Here, we extend th…
View article: Scaffolding Creativity or Homogenizing Outputs?: GPT-based Virtual TA’s Impact on Student Ideation in Graduate Education
Scaffolding Creativity or Homogenizing Outputs?: GPT-based Virtual TA’s Impact on Student Ideation in Graduate Education Open
The rapid integration of large language models in education presents both opportunities and challenges for creative ideation in graduate learning. This quasi-experimental study examines JeepyTA, a GPT-powered teaching assistant and discuss…
View article: The TITAN-X Platform Integrates Big Data, Artificial Intelligence, Bioinformatics, and Advanced Computational Modeling to Understand Immune Responses and Develop the Next Wave of Precision Medicines
The TITAN-X Platform Integrates Big Data, Artificial Intelligence, Bioinformatics, and Advanced Computational Modeling to Understand Immune Responses and Develop the Next Wave of Precision Medicines Open
The TITAN-X Precision Medicine Platform was engineered to rapidly, fully, and efficiently utilize large-scale immunology datasets, including public data, in drug discovery and development. TITAN-X integrates big data with artificial intell…
View article: A systematic review of concussion education, knowledge, and attitudes in football
A systematic review of concussion education, knowledge, and attitudes in football Open
Detecting concussion during football games is difficult due to the complexity of the condition. Medical staff may only enter the field to assess players when the injury is recognised by the referee. With no temporary concussion substitutio…
View article: De-identifying student personally identifying information in discussion forum posts with large language models
De-identifying student personally identifying information in discussion forum posts with large language models Open
Purpose This study aims to evaluate the effectiveness of three large language models (LLMs), GPT-4o, Llama 3.3 70B and Llama 3.1 8B, in redacting personally identifying information (PII) from forum data in massive open online courses (MOOC…
View article: Qualitative Coding with GPT-4
Qualitative Coding with GPT-4 Open
This study explores the potential of the large language model GPT-4 as an automated tool for qualitative data analysis by educational researchers, exploring which techniques are most successful for different types of constructs. Specifical…
View article: Unpacking the Impact of Generative AI Feedback: Divergent Effects on Student Performance and Self-Regulated Learning
Unpacking the Impact of Generative AI Feedback: Divergent Effects on Student Performance and Self-Regulated Learning Open
Generative AI (Gen AI) feedback offers unprecedented opportunities to personalize and scale feedback in educational contexts. However, its effects on student learning may vary depending on the context and how it interacts with students' se…
View article: ABROCA Distributions For Algorithmic Bias Assessment: Considerations Around Interpretation
ABROCA Distributions For Algorithmic Bias Assessment: Considerations Around Interpretation Open
Algorithmic bias continues to be a key concern of learning analytics. We\nstudy the statistical properties of the Absolute Between-ROC Area (ABROCA)\nmetric. This fairness measure quantifies group-level differences in classifier\nperforman…
View article: The Confrustion Constellation: A New Way of Looking at Confusion and Frustration
The Confrustion Constellation: A New Way of Looking at Confusion and Frustration Open
There has been considerable research on confusion and frustration that has treated them as two unitary constructs, distinct from each other. In this article, we argue that there is instead a constellation of different types of confusion an…
View article: Effect of Physiologically Relevant Dehydration on the Dielectric Properties of Ground Beef
Effect of Physiologically Relevant Dehydration on the Dielectric Properties of Ground Beef Open
Readily available animal tissue, such as ground beef, is a convenient material to represent the dielectric properties of biological tissue when validating microwave imaging and sensing hardware and techniques. The reliable use of these mat…
View article: Stirred Not Shaken: A Longitudinal Pilot Study of Head Kinematics and Cognitive Changes in Horseracing
Stirred Not Shaken: A Longitudinal Pilot Study of Head Kinematics and Cognitive Changes in Horseracing Open
The purpose of this longitudinal pilot study was to add to the body of research relating to head kinematics/vibration in sport and their potential to cause short-term alterations in brain function. In horseracing, due to the horse’s moveme…
View article: Cultural bias and cultural alignment of large language models
Cultural bias and cultural alignment of large language models Open
Culture fundamentally shapes people’s reasoning, behavior, and communication. As people increasingly use generative artificial intelligence (AI) to expedite and automate personal and professional tasks, cultural values embedded in AI model…
View article: Gaming the system mediates the relationship between gender and learning outcomes in a digital learning game
Gaming the system mediates the relationship between gender and learning outcomes in a digital learning game Open
Digital learning games have been increasingly adopted in classrooms to facilitate learning and to promote learning outcomes. Contrary to common beliefs, many digital learning games can be more effective for female students than male studen…
View article: Detecting Unsuccessful Students in Cybersecurity Exercises in Two Different Learning Environments
Detecting Unsuccessful Students in Cybersecurity Exercises in Two Different Learning Environments Open
This full paper in the research track evaluates the usage of data logged from cybersecurity exercises in order to predict students who are potentially at risk of performing poorly. Hands-on exercises are essential for learning since they e…
View article: A Step Towards Adaptive Online Learning: Exploring the Role of GPT as Virtual Teaching Assistants in Online Education
A Step Towards Adaptive Online Learning: Exploring the Role of GPT as Virtual Teaching Assistants in Online Education Open
As student learning transitions to being increasingly 24/7, online courses struggle to provide support for learners on the same schedule. Human TAs are bound by time constraints and are often available only during limited working hours. Th…
View article: Comparison of Three Programming Error Measures for Explaining Variability in CS1 Grades
Comparison of Three Programming Error Measures for Explaining Variability in CS1 Grades Open
Programming courses can be challenging for first year university students, especially for those without prior coding experience. Students initially struggle with code syntax, but as more advanced topics are introduced across a semester, th…
View article: Navigating Compiler Errors with AI Assistance - A Study of GPT Hints in an Introductory Programming Course
Navigating Compiler Errors with AI Assistance - A Study of GPT Hints in an Introductory Programming Course Open
We examined the efficacy of AI-assisted learning in an introductory\nprogramming course at the university level by using a GPT-4 model to generate\npersonalized hints for compiler errors within a platform for automated\nassessment of progr…
View article: The Confrustion Constellation: A New Way of Looking at Confusion and Frustration
The Confrustion Constellation: A New Way of Looking at Confusion and Frustration Open
There has been considerable research on confusion and frustration that has treated them as two unitary constructs, distinct from each other. In this article, we argue that there is instead a constellation of different types of confusion an…
View article: Evaluating Algorithmic Bias in Models for Predicting Academic Performance of Filipino Students
Evaluating Algorithmic Bias in Models for Predicting Academic Performance of Filipino Students Open
Algorithmic bias is a major issue in machine learning models in educational contexts. However, it has not yet been studied thoroughly in Asian learning contexts, and only limited work has considered algorithmic bias based on regional (sub-…
View article: Using Large Language Models to Detect Self-Regulated Learning in Think-Aloud Protocols
Using Large Language Models to Detect Self-Regulated Learning in Think-Aloud Protocols Open
Think-aloud protocols are a common method to study self-regulated learning (SRL) during learning by problem-solving. Previous studies have manually transcribed and coded students' verbalizations, labeling the presence or absence of SRL str…