Computer assisted assessment (CAA) objective question has been proven to be able to overcome weaknesses in the evaluation process using paper. Problems that can be overcome include reducing the time needed for correction and the burden of the process of handling thousands of participants simultaneously. However, the preparation for objective questions still constrained by the provision of parallel questions. Parallel questions are made so that each examinee gets a different question but has the same level of difficulty. Manually creating parallel questions at this time is still experiencing problems, that is, in addition to costly, it also has problems when making parallel questions with the same level of difficulty. Therefore several researchers develop the Automatic Item Generation system to overcome these problems. Automatic Item Generation developed in this paper is used to make parallel questions for mathematical problems. The parallel questions can be generated as the AIG system has 3 components, namely stem, variables and options that can be dynamically changed using variables mapping, combination and permutation. The result is that the system is able to generate 70% of the variant questions from dataset questions of junior high school.
[1]
Janet Hughes,et al.
Formative Automated Computer Testing (FACT)
,
2002,
Br. J. Educ. Technol..
[2]
Enrique Alfonseca,et al.
Application of the Bleu algorithm for recognising textual entailments
,
2005
.
[3]
Ku-Yaw Chang,et al.
Online math word problem test system based on dynamic item generation mechanism
,
2010,
2010 International Computer Symposium (ICS2010).
[4]
Rada Mihalcea,et al.
Text-to-Text Semantic Similarity for Automatic Short Answer Grading
,
2009,
EACL.
[5]
Benno Stein,et al.
The Eras and Trends of Automatic Short Answer Grading
,
2015,
International Journal of Artificial Intelligence in Education.
[6]
Mark J. Gierl,et al.
Using Automated Processes to Generate Test Items And Their Associated Solutions and Rationales to Support Formative Feedback
,
2015,
IxD&A.
[7]
Yan Tian.
Online Automated Assessment of Student English-Chinese Translation
,
2009,
2009 WRI World Congress on Computer Science and Information Engineering.