Image and text analytic systems for accessible online learning

Li, Jiaxi

Permalink

https://hdl.handle.net/2142/120301 Copy

Description

Title

Image and text analytic systems for accessible online learning

Author(s)

Li, Jiaxi

Issue Date

2023-04-21

Director of Research (if dissertation) or Advisor (if thesis)

• Nahrstedt, Klara
• Angrave, Lawrence

Department of Study

Computer Science

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Online Learning
• Accessibility
• Image Analysis
• Text Analysis

Abstract

Online learning has been widely used for college-level education in recent years. Although many course platforms offer accessible features such as closed captioning and embedded forums, they are not sufficient to satisfy the demands of students who are deaf and hard of hearing, or are blind or have low vision, students who have difficulty attending in-person lectures, and students who have insufficient prerequisite knowledge. To provide an interactive, accessible, and inclusive learning experience for all students, image and text analytic systems were deployed on ClassTranscribe, a web-based learning platform, to extract useful image and text content from lecture videos in an accurate and efficient manner. Reusing, remixing and transforming on the extracted items enables the generation of multimodal accessibility features including 1) Visual-based lecture delivery, 2) Audio-based lecture delivery, and 3) A glossary application. Preliminary user study results indicated a general positive opinion among students who have utilized the accessibility features for lecture learning.

Graduation Semester

2023-05

Type of Resource

Thesis

Copyright and License Information

Copyright 2023 Jiaxi Li

Owning Collections