Skip to content

Five-category taxonomy of keystroke features for writing-process analysis

Research Method · All research methods
Evidence · no claims cited

Description

The article organizes keystroke-log features drawn from prior literature into five groups: "features related to timings of pauses, revisions, typing bursts, verbosity, and other (non-typing) events". Pause features include IKI metrics and long-pause percentages; revision features cover backspaces and leading-edge versus in-text revisions; fluency features capture bursts; verbosity features count keystrokes and words plus 30-s variability measures; other-event features include focus shifts and cut/paste/jump durations. The study extracted 54 features in these categories from Inputlog raw logs for prediction modeling.

Accounts

  • Five-category taxonomy of keystroke features for writing-process analysis: The article organizes keystroke-log features drawn from prior literature into five groups: "features related to timings of pauses, revisions, typing bursts, verbosity, and other (non-typing) events". Pause features include IKI metrics and long-pause percentages; revision features cover backspaces and leading-edge versus in-text revisions; fluency features capture bursts; verbosity features count keystrokes and words plus 30-s variability measures; other-event features include focus shifts and cut/paste/jump durations. The study extracted 54 features in these categories from Inputlog raw logs for prediction modeling. (Rianne Conijn et al. (2022))

Claims

-

Key Sources

  • Rianne Conijn, Christine Cook, Menno van Zaanen, Luuk Van Waes. (2022). Early prediction of writing quality using keystroke logging. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-021-00268-w
Page metadata
Field Value
type research-method
id five-category-taxonomy-of-keystroke-features-for-writing-process-analysis
title Five-category taxonomy of keystroke features for writing-process analysis
description The article organizes keystroke-log features drawn from prior literature into five groups: "features related to timings of pauses, revisions, typing bursts, verbosity, and other (non-typing) events".
status review
generated by process:settle-candidates on 2026-10-27
trust unverified — no one has confirmed this page's content

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