Instructor co-designed tagging transforms raw LMS log data into structured event data reflecting course design and temporal context¶

Claim · All claims
Evidence · 1 study · design r1 · q2
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? During CLICKSTREAM prototyping, learning scientists and instructors co-developed a course-specific tagging schema (resource type, content topic, coverage date, expected timing) that, when mapped to LMS events, transformed raw log data into structured event data reflecting course design and temporal context. → tagging-process

Evidence¶

tagging-process¶

Bernacki, M.L., and Plumley, R.D. (2026, February). CLICKSTREAM: Essential educational infrastructure to promote student learning and educational theory development. Digital Promise. https://doi.org/10.51388/20.500.12265/285

q2 · i? · design · r1

Descriptive account of the CLICKSTREAM prototyping process, in which learning scientists analyzed instructors' syllabi and schedules, tagged all Canvas assets, and aligned the schema to a generalizable before-during-after framework. The authors report that this "transformed raw log data into structured event data." No empirical evaluation of the process is reported.

"The tagging framework was then mapped to LMS events (e.g., page views, file downloads, assignment submissions) to create enriched student interaction data. This process transformed raw log data into structured event data that reflects not only the underlying course design but also the temporal context of students' engagement"

Discussion¶

Related Claims¶

• Prediction algorithms forecast student achievement from small windows of data, more accurately when data are enriched with instructional design and learning-process detail — a broader claim this one bears on
• Enriched DLP data enable two types of theory testing: sustained observation of individuals in a single setting and modeling the same type of learner across contexts — related
• LMS log analysis showed groups spent roughly 9 days to 2 weeks per module after M1, and completed implementation (M5) faster than expected — related
• LMS process indicators documented adaptive engagement during the eight-week intervention, with most experimental students reaching mastery by unit end — related
• A proposed three-part process-evidence submission (deliverable, AI interaction logs, video reflection) shifts displacement upstream rather than eliminating it — related
• In classroom video labeling, high raw agreement (often exceeding 90%) co-occurred with low chance-corrected κ due to temporal misalignment — related
• Audit finds the stored context fields do not operationally distinguish contextual-scope Types C and D — related
• Epistemic network analysis provides a better account of temporal patterns between socio-cognitive events than coding-and-counting — related