Ontology-based Testing System for Evaluation ...

In the education system the control of knowledge is always of primary importance and is complex interaction process between a teacher and a student. Today computer-aided testing of knowledge becomes very popular because the test’s results do not depend on the subjective opinion of a teacher. Using traditional tests suggests choosing questions of closed form when several variants of the answer are suggested, one of which is correct and should be selected. It is supposed to use them adequately only in terms of strictly formally asked questions. It leads to absolutely simple questions. But knowledge appropriation includes not only (and not so much) memorizing priori veritable facts but the capability to understanding general phenomena, tendencies. To control this knowledge “open" (without the options) test tasks are more effective. In this paper we have presented an ontology-based text mining approach for the automatic evaluation of a student’s answers on the native Language (the Kazakh language). The testing system combined the features of different tests types and formats. The use of intelligent algorithms can also dynamically change the system of evaluation and the test circuit, which significantly improves the quality and speed of testing.