Abstract
Reading comprehension is often assessed by having students read passages and administering a test that assesses their understanding of the text. Shorter assessments may fail to give a full picture of comprehension ability while more thorough ones can be time consuming and costly. This study used data from a conversational intelligent tutoring system (AutoTutor) to assess reading comprehension ability in 52 low-literacy adults who interacted with the system. We analyzed participants’ accuracy and time spent answering questions in conversations in lessons that targeted four theoretical components of comprehension: Word, Textbase, Situation Model, and Rhetorical Structure. Accuracy and answer response time were analyzed to track adults’ proficiency for comprehension components, and we analyzed whether the four components predicted reading grade level. We discuss the results with respect to the advantages that a conversational intelligent tutoring system assessment may provide over traditional assessment tools and the linking of theory to practice in adult literacy.
Highlights
Tests of reading comprehension are widely used both in and out of the classroom for a variety of reasons
To better understand the potential of AutoTutor as a formative assessment for reading comprehension, the present study examined the use of AutoTutor in a sample of heterogeneous adult learners with low literacy skills
The means and standard errors of accuracy and time for questions within each of the four theoretical level categories are shown in Figs. 2 and 3
Summary
Tests of reading comprehension are widely used both in and out of the classroom for a variety of reasons. Practitioners, and others may desire a way to monitor progress, to detect and diagnose reading difficulties, or to test cognitive skills that underlie reading development and disorders Each of these reasons requires an accurate assessment of comprehension. Standardized reading comprehension tests, such as Woodcock–Johnson (Woodcock et al 2001), have historically provided a measure of comprehension ability using a series of passages and conventional assessment techniques, such as multiple choice, cloze, or spoken retelling (Fletcher 2006) These techniques offer many advantages to the extent that they are validated psychometrically, can be and quickly administered, and have a long history of being administered to large numbers of students.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
