Monitoring drop-out rates at specific pages identified difficult text, and revising those pages lowered drop-out rates back to normal¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2016 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Higher drop-out rates at specific pages hinted at difficulties in the text, and revising the text at those pages led to lower (normal) drop-out rates. → Gerhard Weber & Peter Brusilovsky 2016

Evidence¶

Gerhard Weber & Peter Brusilovsky 2016¶

Gerhard Weber & Peter Brusilovsky. (2016). ELM-ART – An Interactive and Intelligent Web-Based Electronic Textbook. Int J Artif Intell Educ 26. https://doi.org/10.1007/s40593-015-0066-8

q2 · i? · design · r2

Longitudinal log monitoring of ELM-ART usage rather than a controlled study; the authors state they continued to monitor user data and were interested in drop-outs. Page-level drop-out spikes were used to revise text, after which drop-out rates at those pages returned to normal. No effect size is printed.

"However, we discovered that some higher drop out rates at specific pages offer a hint to difficulties in the text. This information was used to revise the text at some pages, which, in turn, led to lower (normal) drop-out rates at these pages."

Discussion¶

Related Claims¶

• Using at least one feature raised students' multiple choice question attempt rate to 89 percent and eliminated the drop on hard assignments, with a significant feature-use × difficulty interaction — related
• Pre-tests reduced adult learners' persistence in a MOOC, though they improved post-test scores among those who completed it — related
• Multimedia initial instruction lowers students' perceived difficulty of problems across instruction, practice, and posttest phases — related
• Students show signs of dropout risk early in high school, and schools that reach out in the ninth-grade year can keep them on track to graduate — related