z-logo
open-access-imgOpen Access
Generating Parallel Mathematic Items Using Automatic Item Generation
Author(s) -
Teguh Bharata Adji,
Feddy Setio Pribadi,
Hendro Prabowo,
Raden Rosnawati,
Ariyadi Wijaya
Publication year - 2018
Language(s) - English
Resource type - Conference proceedings
DOI - 10.26499/iceap.v1i1.78
Subject(s) - computer science , process (computing) , permutation (music) , machine learning , artificial intelligence , programming language , physics , acoustics
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.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here
Accelerating Research

Address

John Eccles House
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom