Course-specific prediction models may outperform institution-wide one-size-fits-all models because instructional conditions vary¶

Claim · All claims
Evidence · 1 study · design r? · q2
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? SPPA builds course-specific predictive models rather than institutional models, on the argument that instructional conditions vary across disciplines, courses and instructors. → Alalawi 2024

Evidence¶

Alalawi 2024¶

Alalawi, K., Athauda, R., & Chiong, R. (2024). An Extended Learning Analytics Framework Integrating Machine Learning and Pedagogical Approaches for Student Performance Prediction and Intervention. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-024-00429-7

q2 · i? · design · r?

Design rationale from the Predictive Models section, citing Choi et al. (2018) and Gašević et al. (2016); related work notes Milliron et al. similarly argue for institution-specific models. The article asserts this rationale rather than directly comparing model portability in this study.

"SPPA creates course-specific predictive models instead of institutional models—taking into consideration the instructional conditions, which vary across disciplines, courses, and instructors' preferences, instead of targeting a one-size-fits-all predictive model (Choi et al., 2018; Gašević et al., 2016)."

Discussion¶

Related Claims¶

• A self-service course-level framework lowers the infrastructure barrier to piloting learning analytics interventions — related
• Discipline-general academic vocabulary (AWL use) supports cognitive engagement identification and may aid generalization across courses — reports the opposite
• Academics piloting SPPA provided effective interventions and held positive views of the framework — related