Evaluation of Language Feedback Methods for Student Videos of American Sign Language

Abstract

This research investigates how to best present video-based feedback information to students learning American Sign Language (ASL); these results are relevant not only for the design of a software tool for providing automatic feedback to students but also in the context of how ASL instructors could convey feedback on students’ submitted work. It is known that deaf children benefit from early exposure to language, and higher levels of written language literacy have been measured in deaf adults who were raised in homes using ASL. In addition, prior work has established that new parents of deaf children benefit from technologies to support learning ASL. As part of a long-term project to design a tool to automatically analyze a video of a students’ signing and provide immediate feedback about fluent and non-fluent aspects of their movements, we conducted a study to compare multiple methods of conveying feedback to ASL students, using videos of their signing. Through two user studies, with a Wizard-of-Oz design, we compared multiple types of feedback in regard to users’ subjective judgments of system quality and the degree students’ signing improved (as judged by an ASL instructor who analyzed recordings of students’ signing before and after they viewed each type of feedback). The initial study revealed that displaying videos to students of their signing, augmented with feedback messages about their errors or correct ASL usage, yielded higher subjective scores and greater signing improvement. Students gave higher subjective scores to a version in which time-synchronized pop-up messages appeared overlaid on the student's video to indicate errors or correct ASL usage. In a subsequent study, we found that providing images of correct ASL face and hand movements when providing feedback yielded even higher subjective evaluation scores from ASL students using the system.