Development and testing of an ARSD algorithm: Read, Understand, Learn, & Excel (Kucheria et al., 2019)
online resourceposted on 2019-06-06, 23:23 authored by Priya Kucheria, McKay Moore Sohlberg, Jason Prideaux, Stephen Fickas
Purpose: An important predictor of postsecondary academic success is an individual’s reading comprehension skills. Postsecondary readers apply a wide range of behavioral strategies to process text for learning purposes. Currently, no tools exist to detect a reader’s use of strategies. The primary aim of this study was to develop Read, Understand, Learn, & Excel, an automated tool designed to detect reading strategy use and explore its accuracy in detecting strategies when students read digital, expository text.
Method: An iterative design was used to develop the computer algorithm for detecting 9 reading strategies. Twelve undergraduate students read 2 expository texts that were equated for length and complexity. A human observer documented the strategies employed by each reader, whereas the computer used digital sequences to detect the same strategies. Data were then coded and analyzed to determine agreement between the 2 sources of strategy detection (i.e., the computer and the observer).
Results: Agreement between the computer- and human-coded strategies was 75% or higher for 6 out of the 9 strategies. Only 3 out of the 9 strategies–previewing content, evaluating amount of remaining text, and periodic review and/or iterative summarizing–had less than 60% agreement.
Conclusion: Read, Understand, Learn, & Excel provides proof of concept that a reader’s approach to engaging with academic text can be objectively and automatically captured. Clinical implications and suggestions to improve the sensitivity of the code are discussed.
Supplemental Material S1. Research assistant training protocol.
Supplemental Material S2. Visual guide: This guide highlights the steps involved in matching coded behaviors to strategies.
Kucheria, P., Sohlberg, M. M., Prideaux, J., & Fickas, S. (2019). Read, Understand, Learn, & Excel: Development and testing of an automated reading strategy detection algorithm for postsecondary students. American Journal of Speech-Language Pathology, 28, 1257–1267. https://doi.org/10.1044/2019_AJSLP-18-0181
This study was supported by the National Science Foundation PFI-AIR TT Grant 1640492, awarded to McKay Moore Sohlberg, at the University of Oregon.
readingliteracypostsecondarystudentsRead, Understand, Learn, & Exceldevelopmenttestingautomatedstrategydetectionalgorithmpredictorsuccesscomprehensionskillstextacademicbehavioralprocesslearningeducationreadertoolaccuracydigitalexpositoryiterativedesigncomputerundergraduatecollegedataproof of conceptapproachobjectiveautomaticclinicalEducational Technology and Computing