Abstract—Peer assessment can help address the problem of
imbalance between teachers and students in China’s higher
education environment, and it can also effectively promote the
development of learners' various abilities. However, previous
studies indicate that students generally ascribe more value to
teacher assessment than to peer assessment. Accordingly,
methods to improve the efficiency of peer assessment demand
more attention. This study explored the validity of
peer-assessment and the acceptance of peer assessment via case
collaborative out-of-class learning in a “natural language
processing” course. Experiments showed a statistically
significant correlation, but no significant difference, for
peer-assessment between-groups and the teacher assessment.
Peer-assessment can be used as a reference for the teacher
assessment. On the contrary, there was a statistically significant
difference but no significant correlation for the within-group
assessment and the teacher assessment. Additionally, students
reported that they found the peer-assessment based on
collaborative out-of-class learning helpful and felt they
benefited from peer assessment during teaching practice.
Index Terms—Collaborative out-of-class learning, natural
language processing, peer-assessment, engineering education.
Meixiu Lu is with School of Information Science and Technology/School
of Cyber Security, Guangdong University of Foreign Studies, Guangzhou,
510420, China (e-mail: lmx1977@163.com).
Manzhen Yang is with School of English and Education, Guangdong
University of Foreign Studies, Guangzhou, 510420, China (corresponding
author: Manzhen Yang; e-mail:199610576@oamail.gdufs.edu.cn).
Xia Li is with Laboratory of Language Engineering and Computing,
Guangdong University of Foreign Studies, Guangzhou, 510420, China
(e-mail: 200211025@oamail.gdufs.edu.cn).
Cite: Meixiu Lu, Manzhen Yang, and Xia Li, "A Study on Peer-Assessment Based on Collaborative Out-of-Class Learning," International Journal of Information and Education Technology vol. 8, no. 10, pp. 748-753, 2018.