Using Generative Artificial Intelligence to Develop Attitude Scales

• In Event: AERA Roundtable Session Saturday 1:30 pm Four Seasons Ballroom 2-3
  In Roundtable Session: Multidisciplinary Measurement Using Rasch Modeling (Table 4)

Abstract

This study explores the integration of generative artificial intelligence (AI) and Rasch measurement theory to develop an attitude scale measuring attitudes toward censorship. By combining automated item generation (AIG) with advanced AI models such as ChatGPT-4, the research tries to streamline the item development process and improve the precision and validity of attitude measurements. The study involved university students from southeastern universities completing surveys generated by AI, which included comprehensive items reflecting diverse viewpoints on censorship. Rasch analysis was conducted to calibrate the items and establish a robust scale. This innovative approach demonstrates the potential of AI in creating relevant attitude scales, advancing methodological frameworks, and practical applications in social psychology and educational research.

Authors

• Eunji Lee, University of Georgia

• George Engelhard, University of Georgia

• Ye Yuan, Graduate Management Admission Council