Human-Centered Design for AI-based Automatically Generated Assessment Reports: A Systematic Review
Project Overview
The document explores the integration of generative AI in K-12 STEM education through the design and implementation of Automatically Generated Assessment Reports (AutoRs) aimed at improving formative assessments. It emphasizes the necessity of a user-centered design to alleviate cognitive load on teachers while providing actionable insights on student performance. Findings reveal that many current AutoRs fail to employ effective design principles, resulting in increased cognitive demands and diminished teacher engagement. To address these issues, a new framework is proposed that seeks to enhance the development of AutoRs, ensuring they balance usability with functionality. This approach aims to empower educators by providing clearer, more effective assessment tools that support student learning and performance analysis. Overall, the document underscores the potential of generative AI to transform educational assessments by making them more intuitive and user-friendly, ultimately fostering a better teaching and learning environment.
Key Applications
Automatically Generated Assessment Reports (AutoRs)
Context: K-12 STEM classrooms, targeted at teachers and students.
Implementation: AutoRs are designed to provide synthesized, interpretable, and actionable insights into student performance, using AI and human-centered design principles.
Outcomes: AutoRs aim to improve teachers' decision-making, reduce cognitive load, and foster personalized learning experiences for students.
Challenges: Many existing AutoRs fail to effectively present information, leading to high cognitive demands and limited teacher engagement.
Implementation Barriers
Cognitive Load
Teachers experience information overload when interpreting assessment results from AutoRs, which can be complex and multifaceted.
Proposed Solutions: Implement user-centered designs that prioritize clear and intuitive visualizations to reduce cognitive load.
Technology Integration
Insufficient integration of AI capabilities in existing AutoRs may limit their effectiveness and usability for teachers.
Proposed Solutions: Enhance AI functionalities in AutoRs to automate routine tasks and provide clear feedback mechanisms.
Project Team
Ehsan Latif
Researcher
Ying Chen
Researcher
Xiaoming Zhai
Researcher
Yue Yin
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Ehsan Latif, Ying Chen, Xiaoming Zhai, Yue Yin
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