Premium
Modeling Basic Writing Processes From Keystroke Logs
Author(s) -
Guo Hongwen,
Deane Paul D.,
Rijn Peter W.,
Zhang Mo,
Bennett Randy E.
Publication year - 2018
Publication title -
journal of educational measurement
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.917
H-Index - 47
eISSN - 1745-3984
pISSN - 0022-0655
DOI - 10.1111/jedm.12172
Subject(s) - keystroke logging , fluency , log normal distribution , mathematics education , psychology , computer science , composition (language) , natural language processing , cognitive psychology , statistics , mathematics , linguistics , philosophy , operating system
The goal of this study is to model pauses extracted from writing keystroke logs as a way of characterizing the processes students use in essay composition. Low‐level timing data were modeled, the interkey interval and its subtype, the intraword duration, thought to reflect processes associated with keyboarding skills and composition fluency. Heavy‐tailed probability distributions (lognormal and stable distributions) were fit to individual students' data. Both density functions fit reasonably well, and estimated parameters were found to be robust across prompts designed to assess student proficiency for the same writing purpose. In addition, estimated parameters for both density functions were statistically significantly associated with human essay scores after accounting for total time spent writing the essay, a result consistent with cognitive theory on the role of low‐level processes in writing.