Loading...
Using natural language processing to predict item response times and improve test construction
Baldwin, Peter Yaneva, Victoria Mee, Janet Clauser, Brian E Ha, Le An
Baldwin, Peter
Yaneva, Victoria
Mee, Janet
Clauser, Brian E
Ha, Le An
Editors
Other contributors
Affiliation
Epub Date
Issue Date
2020-02-24
Submitted date
Subjects
Alternative
Abstract
In this article, it is shown how item text can be represented by (a) 113 features quantifying the text's linguistic characteristics, (b) 16 measures of the extent to which an information‐retrieval‐based automatic question‐answering system finds an item challenging, and (c) through dense word representations (word embeddings). Using a random forests algorithm, these data then are used to train a prediction model for item response times and predicted response times then are used to assemble test forms. Using empirical data from the United States Medical Licensing Examination, we show that timing demands are more consistent across these specially assembled forms than across forms comprising randomly‐selected items. Because an exam's timing conditions affect examinee performance, this result has implications for exam fairness whenever examinees are compared with each other or against a common standard.
Citation
Baldwin, P., Yaneva, V., Mee, J., Clauser, B. E., and Ha, L. A. (2020) Using natural language processing to predict item response times and improve test construction, Journal of Educational Measurement, https://doi.org/10.1111/jedm.12264
Publisher
Research Unit
PubMed ID
PubMed Central ID
Embedded videos
Additional Links
Type
Journal article
Language
en
Description
Series/Report no.
ISSN
0022-0655
EISSN
1745-3984