Generative AI Chatbot for Large-Scale Assessment Data Analysis

• In Event: Innovation Demonstration I

Abstract

We fine-tuned the generative AI model and developed specific chatbots to help coding for large-scale assessment (LSA) data analyses. The chatbot focuses on helping with NCES LSA data analysis programming with the R package EdSurvey. We focused on methods that write the codes for analyses and debug the written codes.

Authors

• Sinan Yavuz, American Institutes for Research

• Blue Webb, AMERICAN INSTITUTES FOR RESEARCH

• Paul Bailey, American Institutes for Research

• Ting Zhang, American Institutes for Research

• Yuqi Liao, American Institutes for Research

• Emmanuel Sikali