Over the full writing process, only one of 54 keystroke features (percentage of long pauses between words) correlates significantly with final writing grade in ESL academic summaries¶

Claim · All claims
Evidence · 1 study · associational r1 · q2 · i2 medium
Currency · newest study 2022 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i2 For keystrokes measured over the full writing process, only the percentage of long pauses between words was significantly related to final grade, and the relation was small and positive (r = 0.22). → Rianne Conijn 2022

Evidence¶

Rianne Conijn 2022¶

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

q2 · i2 · associational · r1

Correlational analysis (RQ1) of 54 keystroke features against final grade for 126 ESL students performing a timed academic summary task. Only "the percentage of long pauses between words ( r = 0.22)" was significant over the full process; the authors note p-values are exploratory given multiplicity.

"For the keystrokes measured over the full writing processes, only one significant correlation was found. Final grade had a small positive relation to the percentage of long pauses between words ( r = 0.22). Thus, more pauses between words are related to a higher writing quality."

Discussion¶

Related Claims¶

• Important keystroke features for classifying at-risk writers differ by stage: early models emphasize focus shifts and initial pause, later models emphasize inter-keystroke-interval variance — related
• Which keystroke features correlate with writing grade changes across stages of the writing process: pause-variance and focus-shift features matter early, sentence-transition and event features later — related
• The relationship between keystroke data and writing quality may be less clear than previously posited — a broader claim this one bears on
• Keystroke-feature regression models fail to predict final writing grade at any point during the writing process — reports the opposite
• Binary classification of students who might need support from keystroke data only slightly exceeds the majority-class baseline (highest AUC 0.57) — related