Trace parser with action library and process library for measuring SRL from multi-channel data

Research Method · All research methods
Evidence · 9 claims (7 for, 1 mixed, 1 against) · 2 studies (2 design), q2–q3 · 0 of 2 report an effect size · 9 claims rest on one study

Description

A trace-based measurement protocol that converts raw multi-channel trace data into SRL processes. Its trace parser has two components: "the action library and the process library" — the action library labels raw log data with 12 learning actions, and the process library detects SRL processes from action sequences. The study examined "the eight groups of SRL processes: four groups of metacognitive and four groups of cognitive processes, including Orientation, Planning, Monitoring, Evaluation, First-reading, Re-reading, Elaborating and Organising", grounded in Bannert's (2007) theoretical framework and validated through theory-driven and data-driven perspectives.

Accounts

• Trace parser with action library and process library for measuring SRL from multi-channel data: A trace-based measurement protocol that converts raw multi-channel trace data into SRL processes. Its trace parser has two components: "the action library and the process library" — the action library labels raw log data with 12 learning actions, and the process library detects SRL processes from action sequences. The study examined "the eight groups of SRL processes: four groups of metacognitive and four groups of cognitive processes, including Orientation, Planning, Monitoring, Evaluation, First-reading, Re-reading, Elaborating and Organising", grounded in Bannert's (2007) theoretical framework and validated through theory-driven and data-driven perspectives. (Yizhou Fan et al. (2022))

Claims

• Eye-tracking data enables detection of more frequent Monitoring and Evaluation processes that navigational and peripheral channels miss [+M]
• Adding peripheral data raises specific transition probabilities in the SRL process map, e.g., Elaboration-to-Monitoring from 24% to 44% [+W]
• Most refinements from adding peripheral data convert First-reading or Re-reading into Organisation, and eye-tracking then corrects many back to First-reading [+W]
• A theory-driven trace-based SRL measurement achieved a match rate of 38.97% with think aloud data when evaluated against think aloud as reference point [+W]
• Adding peripheral data to navigational logs sharply changes the detected distribution of SRL processes, revealing many more Organisation and far fewer First-reading processes [+W]
• The largest source of mismatch between trace-based and think aloud SRL processes was confusion between elaboration/organisation and first-reading processes [-W]
• Adding data channels refines roughly 29–52% of detected SRL process time, measured by a new percent-of-processes-refined metric [+W]
• The combined theory-driven and data-driven validation approach improved the match rate between trace-based SRL processes and think aloud data from 38.97% to 54.24% (training) and 34.54% to 55.09% (testing) [+W]
• Substantial differences existed between the time distribution of trace-extracted and think aloud-coded SRL processes: 41.66% of session duration had no think aloud code while only 3.19% had no trace process [~W]

Related Research Methods

• Coherence analysis framework and its six activity-trace measures
• Newell-inspired time-scale taxonomy for aligning SRL measurement to theorized process duration

Key Sources

• Yizhou Fan, Lyn Lim, Joep van der Graaf, Jonathan Kilgour, Mladen Raković, Johanna Moore, Inge Molenaar, Maria Bannert, Maria Bannert, Dragan Gašević. (2022). Improving the measurement of self-regulated learning using multi-channel data. Metacognition and Learning. https://doi.org/10.1007/s11409-022-09304-z

Page metadata

Field	Value
type	research-method
id	trace-parser-with-action-library-and-process-library-for-measuring-srl-from-multi-channel
title	Trace parser with action library and process library for measuring SRL from multi-channel data
description	A trace-based measurement protocol that converts raw multi-channel trace data into SRL processes.
status	review
generated	by process:settle-candidates on 2026-10-19
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.