Online test paper generation for a web-based mathematics testing environment

Abstract

With the rapid growth of the Internet and mobile devices, Web-based education has become a ubiquitous learning platform in many institutions to provide students with online learning courses and materials through freely accessible educational websites. To make learning effective, it is important to assess and evaluate the proficiency and ability of the learners while they are learning the concepts. Currently, Web-based testing has been popularly used for automatic self-assessment especially in Web-based learning environments. Different from passive course archives like MIT OpenCourseWare, the online courses are interactive and can assess learners automatically on what they have learnt via Web-based testing. The main benefit is that learners can take classes at their own pace and get immediate feedback on their proficiency, unlike traditional classes. In this research, we propose a Web-based Mathematics Testing Environment, which consists of three major components, namely question item calibration, online test paper generation, and automatic solution assessment. Question item calibration calibrates the attributes of each question in the question database. Online test paper generation generates test papers automatically from the question database with online runtime requirement. After the test paper has been answered online, automatic solution assessment can then evaluate the correctness of user answers. This research aims to investigate different multiobjective optimization, data mining and probabilistic techniques for supporting the three components of the Web-based Mathematics testing environment. More specifically, it focuses mainly on online test paper generation, parallel test paper generation, automatic question difficulty calibration and automatic mathematical solution assessment.