Decoding AI: Insights into Answer Variability Using Text Analytics 4:00
Alternative Title
Decoding Artificial Intelligence (AI): Insights into Answer Variability Using Text Analytics 4:00
Contributor
University of Central Florida. Faculty Center for Teaching and Learning; University of Central Florida. Division of Digital Learning; Teaching and Learning with AI Conference (2025 : Orlando, Fla.)
Location
Universal Center
Start Date
29-5-2025 4:00 PM
End Date
29-5-2025 5:00 PM
Publisher
University of Central Florida Libraries
Keywords:
Generative AI; Text analytics; Answer variability; Education technology; Shiny App
Subjects
Artificial intelligence--Educational applications; Artificial intelligence--Computer-assisted instruction; Artificial intelligence--Statistical methods; Artificial intelligence--Study and teaching; Artificial intelligence--Research
Description
Many believe that generative AI platforms have the potential to revolutionize education by providing a personalized supplement to traditional education. Therefore, it is important to investigate the accuracy of output from generative AI platforms and the variations in results from the same prompt on different platforms. We examined differences in answers to statistics questions among several commonly used AI platforms employing text analytics, such as reading level evaluation, word counts, topic modeling, and sentiment analysis. In this session, we will introduce a Shiny App to perform these analytics for output from any generative AI platform.
Language
eng
Type
Presentation
Rights Statement
All Rights Reserved
Audience
Faculty; Students
Recommended Citation
McGee, Monnie, "Decoding AI: Insights into Answer Variability Using Text Analytics 4:00" (2025). Teaching and Learning with AI Conference Presentations. 134.
https://stars.library.ucf.edu/teachwithai/2025/thursday/134
Decoding AI: Insights into Answer Variability Using Text Analytics 4:00
Universal Center
Many believe that generative AI platforms have the potential to revolutionize education by providing a personalized supplement to traditional education. Therefore, it is important to investigate the accuracy of output from generative AI platforms and the variations in results from the same prompt on different platforms. We examined differences in answers to statistics questions among several commonly used AI platforms employing text analytics, such as reading level evaluation, word counts, topic modeling, and sentiment analysis. In this session, we will introduce a Shiny App to perform these analytics for output from any generative AI platform.