Supporting students’ peer assessment using chatbots
Wang, Dennis
Loading…
Permalink
https://hdl.handle.net/2142/108353
Description
Title
Supporting students’ peer assessment using chatbots
Author(s)
Wang, Dennis
Issue Date
2020-05-15
Director of Research (if dissertation) or Advisor (if thesis)
Huang, Yun
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)
Peer Assessment
Chatbot
Conversational Agent
Abstract
Peer assessment is found to be an effective approach for instructors to evaluate students’ learning performance in large classes, and it provides great learning opportunities for stu- dents. However, conducting successful peer assessment remains challenging as peer graders often do not have sufficient guidance to make fair assessment and to provide useful feedback. In this thesis, we explore the potential of using a chatbot to facilitate the execution of peer assessment. We conducted two studies in two university courses. The first one was a within- subject study, which focused on understanding the effect of chatbot use for peer assessment over time. The second was a between-subject study, which addressed the differences between providing guidance by a chatbot and giving suggestions through a regular form. Our results show that, using a chatbot for several times, students improved the performance of conducting peer assessment by providing more accurate scores that were closer to the TAs’ scores. Also, when the chatbot provided guidance, high-performing peer graders were more likely to give positive comments with constructive suggestions than low-performing peer graders did. Our results provide insights into designing interaction technologies to improve both the quality of peer assessment and students’ learning.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.