Thesis Defense Announcement
College of Arts and Sciences announces the Final Thesis Defense of
for the Degree of Master of Science
March 22, 2019 at 10:00 AM in FedEx Institute of Technology, Room 403A
Advisor: Andrew Olney
Improving Reading Comprehension Of Science Texts With Computer Generated Cloze Item Practice
ABSTRACT: Whaley, Davis. MS. The University of Memphis. May 2018. Improving science comprehension with computer-generated cloze practice. Major Professor: Andrew Olney This study attempted to replicate and extend previous work with computer-generated cloze items. Participants recruited from Amazon Mechanical Turk (N = 562) took a pretest on one of three science topics and then read a text about it. Participants then answered cloze items about the text generated either by a computer, human, or randomly in a 3x3 study. Participants answered the cloze questions using the MoFaCTS adaptive practice system. After a 24-hour delay, reading comprehension was tested using a post-test. The purpose of the study was to see if computer-generated cloze items using rational deletion with natural language processing methods could promote learning and comprehension of science texts compared to human and random conditions. Analysis showed Human scored higher on gain score than Random. Additionally, Machine scored higher than Random in the Circulatory System text.