Leverage digital learning platforms to run unobtrusive randomized experiments on language modifications in math problems¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The article argues that DLPs' adaptability "allows for controlled experimentation with language variations in math problems," providing fertile ground for research on language and mathematics. Because randomization happens in the platform backend, studies "run unobtrusively, as students will just be doing the assignments in a natural online learning environment," and researchers can leverage existing user bases rather than recruiting participants independently. The three platform workflows illustrate study design, deployment, and data export for this purpose.

Design Implications¶

Context¶

Requirements¶

• Access to a DLP with randomization infrastructure and an existing student user base, or independent recruitment for custom content

Constraints¶

• The proposed studies are hypothetical and illustrative; findings are pending empirical validation and generalization across platforms is only suggested

Target Learners¶

• K-12 students in digital math learning environments

Target Learning Goals¶

• improving mathematics learning through language-focused interventions

Related Strategies¶

• Use a 2x2 factorial design to separate the effects of contextual relevance and linguistic detail in word problems
• Conduct a smaller sequence of rapid-cycle studies that build on one another instead of planning a single large confirmatory study
• Use web-based educational platforms to run individual-level randomized experiments in the classroom

Examples¶

-

Key Sources¶

• Wei, X., Wortman, A., Cheng, L., Heffernan, N., Heffernan, C., Murphy, A., Zepeda, C., Motz, B., Jankowski, H., & Roschelle, J. (2024, March). Language and mathematics learning: A comparative study of digital learning platforms. Digital Promise. https://doi.org/10.51388/20.500.12265/206