Browsing by Author "M. Zhaparov"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    PROJECT-BASED CURRICULUM FOR INTERNET OF THINGS ONLINE COURSE
    (СДУ хабаршысы - 2021, 2021) Zh. Mamatnabivev; M. Zhaparov
    Abstract. Nowadays, the applications of the Internet of Things (IoT) are getting popular and the number of internet connecting devices are increasing very fast. Many IoT courses are being taught in educational universities. However, the curriculum of the courses does not answer to the requirements of the industry and market, and students have not enough knowledge if they are getting the course online, where there is no offline lab work. Project based curriculum for online IoT courses is developed and grades of the student projects are compared with the knowledge of the students before project implementation. The comparison results are promising and future works are discussed.
  • Thumbnail Image
    ItemOpen Access
    SENTIMENT ANALYSIS OF UNIVERSITY FEEDBACK OPINION OF STUDENTS ABOUT AN EDUCATIONAL PART IN KAZAKH LANGUAGE USING MULTIBINOMIAL NAIVE BAYES CLASSIFIER
    (СДУ хабаршысы - 2019, 2019) A. Serek; M. Zhaparov
    Abstract. In this paper, the system which identifies the sentiment, (aka meaning) of a kazakh phrase, (whether it is a positive, or a negative) have been implemented using MultiBinomial Naive Bayes Classifier and achieved accuracy approximately 71 % on the dataset about university feedback across students on its educational component in order to help administrative staff to evaluate the current state of education in the university and make some decisions on its basis. We consider it to be a good result, given that the data was small in size, so that there were only few collected samples. The importance of the work that we did not find any paper which performed sentiment analysis using MultiBinomial Naive Bayes classifier on an agglutinative language. It can be argued, that the model can be successfully generalized in other educational organizations pursuing the same cause as it was identified in the above-mentioned rationale. The limitation of the paper is that only one algorithm has been applied to it, and the dataset size is small.