Event Title
Explainable Artificial Intelligence: A Theory-Guided Genetic Programming Model for At-Risk Student Prediction
Start Date
3-2-2021 4:10 PM
End Date
3-2-2021 5:40 PM
Date of Publication
February 2021
Document Type
Presentation
Abstract
The purpose of this experimental research is to investigate the efficacy of explainable artificial intelligence (XAI) implementing theory-guided genetic programming model for at-risk student prediction and retention improvement. The predictive model incorporates human-computer interaction theory, Fink’s Taxonomy of Significant Learning, and evidence-based contributing factors. Purposive and volunteer sampling will be employed to select first-year freshman cohorts (i.e., control and experimental groups) enrolled in an online higher education program over a two-semester period. Educational data mining and feedback surveys are employed for data collection and analysis. Mean values and effect sizes will be reported at the .05 significance level.
Keywords
Retention, Artificial Intelligence
Description
Methodology, Discussant: Grant Morgan
Persistent Identifier
http://hdl.handle.net/10950/2847
Explainable Artificial Intelligence: A Theory-Guided Genetic Programming Model for At-Risk Student Prediction
The purpose of this experimental research is to investigate the efficacy of explainable artificial intelligence (XAI) implementing theory-guided genetic programming model for at-risk student prediction and retention improvement. The predictive model incorporates human-computer interaction theory, Fink’s Taxonomy of Significant Learning, and evidence-based contributing factors. Purposive and volunteer sampling will be employed to select first-year freshman cohorts (i.e., control and experimental groups) enrolled in an online higher education program over a two-semester period. Educational data mining and feedback surveys are employed for data collection and analysis. Mean values and effect sizes will be reported at the .05 significance level.