A scoring rubric for automatic short answer grading system

Somehow, a study conducted by Mohler [5] concluded that the use of large general corpus has a lower performance than a smaller domain corpus. [...]the next studies began to use alternative reference answers to address variations in student answers [23, 24]. [...]pre-processing step is conducted to c...

Full description

Saved in:
Bibliographic Details
Published in:Telkomnika 2019-04, Vol.17 (2), p.763-770
Main Authors: Hasanah, Uswatun, Permanasari, Adhistya Erna, Kusumawardani, Sri Suning, Pribadi, Feddy Setio
Format: Article
Language:English
Subjects:
Algorithms
Artificial intelligence
Automation
Evaluation
Information retrieval
International conferences
Language
Learning
Methods
Natural language processing
Online instruction
Performance evaluation
Research methodology
Researchers
Semantic analysis
Semantics
Studies
Teachers
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Somehow, a study conducted by Mohler [5] concluded that the use of large general corpus has a lower performance than a smaller domain corpus. [...]the next studies began to use alternative reference answers to address variations in student answers [23, 24]. [...]pre-processing step is conducted to clean the answers from noisiness. [...]the performance evaluation is used to measure the level of agreement or value of proximity between the score generated by the system and the score generated by the teacher. 2.2.Dataset The data is in Indonesian and consists of 7 questions with 34 teacher responses as reference answers and 256 student answers in total. [...]we remove stopwords by using the list of ID-Stopwords libraries consisting of 758 words based on research conducted by Tala [38].
ISSN:1693-6930
2302-9293
DOI:10.12928/telkomnika.v17i2.11785