Indexing Analytics to Instances: How Integrating a Dashboard can Support Design Education
Project Overview
The document explores the role of generative AI in education by emphasizing its integration into design education through AI-based multiscale design analytics. It presents a dashboard that links these analytics to students' design work, facilitating improved instructor assessment and feedback while deepening students' comprehension of their design processes and creative strategies. The findings indicate that such analytics can enhance pedagogical practices, allowing for timely interventions that support student learning. However, challenges remain regarding the effective implementation and interpretation of these analytics in educational settings. Overall, the application of generative AI in this context demonstrates significant potential to transform educational practices and outcomes, although it requires careful consideration of its complexities.
Key Applications
Multiscale Design Analytics Dashboard
Context: Design education across various disciplines, including Interactive Art & Design, Mechanical Engineering, and Computer Science, focusing on collaborative design projects where students create, visualize, and annotate their design work. This implementation spans institutions like Texas A&M University and Illinois State University, emphasizing team-based and individual design processes.
Implementation: The multiscale design analytics dashboard was integrated into the project workflow, enabling students to organize their design ideas and visualize their design analytics. Instructors leveraged the dashboard to monitor student progress and assess design effectiveness, facilitating personalized feedback and pedagogical interventions based on observed design structures.
Outcomes: Instructors reported gaining insights into students' design processes, which allowed for timely interventions and personalized feedback. The analytics also helped identify common challenges faced by students across different projects, promoting a better understanding of design effectiveness.
Challenges: Instructors faced challenges in interpreting complex analytics and ensuring effective communication of data insights to students, as well as difficulties in developing universal metrics applicable across the diverse range of design projects and student approaches.
Implementation Barriers
Technical barrier
Difficulty in ensuring that AI-based analytics accurately represent the complexity of students' creative designs.
Proposed Solutions: Continual refinement of the AI models based on instructor feedback and real-world usage to improve accuracy.
Interpretation barrier
Challenges instructors face in understanding the implications of the analytics without proper context.
Proposed Solutions: Providing additional training and resources to help instructors interpret analytics in relation to specific design projects.
Implementation barrier
Integrating the analytics dashboard into existing teaching practices and ensuring all instructors are comfortable using it.
Proposed Solutions: Offering workshops and support for instructors to familiarize them with the dashboard and its functionalities.
Project Team
Ajit Jain
Researcher
Andruid Kerne
Researcher
Nic Lupfer
Researcher
Gabriel Britain
Researcher
Aaron Perrine
Researcher
Yoonsuck Choe
Researcher
John Keyser
Researcher
Ruihong Huang
Researcher
Jinsil Seo
Researcher
Annie Sungkajun
Researcher
Robert Lightfoot
Researcher
Timothy McGuire
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Ajit Jain, Andruid Kerne, Nic Lupfer, Gabriel Britain, Aaron Perrine, Yoonsuck Choe, John Keyser, Ruihong Huang, Jinsil Seo, Annie Sungkajun, Robert Lightfoot, Timothy McGuire
Source Publication: View Original PaperLink opens in a new window
Project Contact: Dr. Jianhua Yang
LLM Model Version: gpt-4o-mini-2024-07-18
Analysis Provider: Openai