Projects
 |  |
|---|---|
 |  |
03 Research Projects
Work-on progress: Measuring Prosocial Behavior in Schools through a Virtual Reality Game: vSchool
UX researcher/Game Designer
Background
VSchool is a research-driven initiative focused on developing and validating a game-based assessment designed to measure prosocial behavior in 4th–6th-grade students. The assessment takes place within an interactive virtual environment that simulates realistic school-based scenarios, aiming to provide educators with an engaging and scalable tool for understanding student behavior.
Project Official Intro:
https://adroit.missouri.edu/project/vschool/
Goal
The primary goal of this project was to ensure that the game interface is intuitive, developmentally appropriate, and aligned with the intended assessment outcomes—capturing meaningful data on prosocial decision-making while maintaining a compelling user experience for children.
Methods
I led the UX research component using a comprehensive, mixed-methods approach to evaluate and iterate on the game design. Methods included:
-
Lab-based usability testing to assess interaction flow and identify pain points
-
Remote usability sessions to ensure accessibility across varied school environments
-
Cognitive walkthroughs and expert reviews of the gameplay experience
-
System Usability Scale (SUS) to benchmark user satisfaction
-
Eye tracking and skin conductance response to analyze engagement and emotional arousal
-
Open-ended surveys and semi-structured interviews with student participants
-
Stakeholder interviews with teachers and school staff to incorporate pedagogical insights
-
Classroom observations to contextualize in-game behaviors and usability in real learning environments
Results
-
Preliminary findings indicate high levels of student engagement and usability, with positive feedback from both students and teachers.
-
Key insights led to actionable design changes that improved interface clarity and emotional engagement.
-
Teacher feedback emphasized the tool’s potential for integration into social-emotional learning (SEL) curricula.
-
The project is ongoing, with planned dissemination through academic conferences and publications.
If you are interested in the game tests, please contact fyu@mail.missouri.edu
Research Projects
A New Method Using LLMs for Keypoints Generation in Qualitative Data Analysis
The screenshot of analysis results:
Research Projects
AI-powered grading system - AutoGrade
Project Investigator
Background
This project explores the integration of Large Language Model (LLM), such as ChatGPT, as a powerful tool for grading assignments within learning management platforms like Canvas. Traditional grading methods often lack the precision and specificity that students require for a deeper understanding of their work. In contrast, ChatGPT, when equipped with appropriate prompts and programmed by instructors, provides a solution that can enhance the grading and feedback process.
This approach enabled the provision of comprehensive feedback aligned with each item of the predefined rubric, facilitating students in pinpointing their strengths and areas for enhancement with precision, ultimately enhancing the overall learning experience. The AI tool can significantly reduce instructors' grading workload by automating assignment evaluation and offering detailed feedback based on predefined criteria.
Goal
Our team has developed an online platform incorporating GPT 4.0 to aid instructors in grading students' assignments efficiently. Throughout this endeavor, we aim to investigate the attitudes, expectations, and concerns of both students and instructors regarding the implementation of this AI grading platform.
The screenshot of the grading application
Feedback provided by AI with detailed feedback that matched the specific criteria we had set
