(сетевой с №3-2015)
(сетевой с №2-2015)
|Articles and journals | Tariffs | Payments | Your profile|
Reducing the complexity of the model of individual and group adaptive testing with multiple choice based on a fuzzy cognitive map
Abstract.The subject of the study is adaptive testing with multiple choice questions. This type of testing allows you to implement a machine assessment of the level of knowledge of the participants is simple and accessible, eliminating errors of evaluating the results. However, the adaptive testing model includes a parameter describing the probability of guessing answers to test tasks, which depends on many factors: the difficulty of the task, the level of knowledge of the learner, the presence of a fine for trying to guess, and the degree to which the participant’s answers with a higher level of knowledge influence the opinions of other participants. in the conditions of individual and group testing. The need to explicitly set this parameter complicates the model and introduces uncertainty in the test results. The introduction of a fuzzy cognitive map, which determines the degree of "pure" and "partial" guessing in response to test tasks, reduces the complexity of the testing model as a result of excluding the explicit probabilistic parameter. Unlike the well-known definitions of a cognitive map, the proposed interpretation is based on models of individual and group adaptive testing with multiple choice. The results of computational experiments in real testing confirmed the effectiveness of the introduction of the map. It was found that fuzzy estimates of the responses of participants with a lower level of knowledge to more complex tasks are more consistent than estimates that require explicit assignment of the probability of "pure" guessing. The method of reducing the complexity of a testing model based on a fuzzy cognitive map can be used both in educational software systems and in intelligent systems and decision support systems that provide for testing with multiple choice.
Keywords: Bloom's taxonomy, interval-valued fuzzy set, cognitive modelling, knowledge assessment, pure guessing, partial guessing, collaborative learning, adaptive testing, cognitive map, logistic model
Article was received:27-12-2018
This article written in Russian. You can find full text of article in Russian here .