DIGITAL LIBRARY
DESIGN AND IMPLEMENTATION OF A WEB-BASED TOOL TO INTEGRATE NATURAL LANGUAGE FEEDBACK IN AUTOMATED ASSESSMENT
DHBW Stuttgart (GERMANY)
About this paper:
Appears in: ICERI2022 Proceedings
Publication year: 2022
Pages: 5769-5774
ISBN: 978-84-09-45476-1
ISSN: 2340-1095
doi: 10.21125/iceri.2022.1427
Conference name: 15th annual International Conference of Education, Research and Innovation
Dates: 7-9 November, 2022
Location: Seville, Spain
Abstract:
The COVID pandemic poses new challenges for higher education institutions, which must increasingly offer distance learning methods.
From this perspective, the automated provision and grading of exercises and exams is gaining greater importance. In addition, many lecturers, especially in computer science, are finding that the previous practice of manually grading exercises or exams is impractical due to the amount of work involved.

Although numerous publications show the use of e-assessment in teaching, there are so far only a few approaches that address the generation of feedback that is understandable for students. To fill this gap, we present in this paper a web-based system for automatic grading of programming exercises or exams in the Java programming language. The system has been used for a growing number of students in many lectures since 2020. The core idea is to use natural language acceptance tests: the teacher creates a set of acceptance tests and the students' solutions are tested using these acceptance tests. In this approach, students get comprehensible and understandable feedback based on the natural language acceptance tests.

In this paper, we describe the architecture of the system and summarize the experience of using the system.
Keywords:
E-assessment tool, automatic assessment, acceptance tests, feedback.