No abstract

The purpose of this research is a comprehensive review of studies towards educational data mining (EDM) in Turkey. For the purpose of this study, graduate theses and articles conducted in Turkey were examined in detail. As a result of the literature review, 48 studies were analyzed in the context of the data mining purpose, the technique used in the study, the purpose of the study, the sample, the data sources and the analysis tool used in the study. In addition, the input variables used in the studies for estimating student achievement in EDM were examined. As a result of the research, it was found that EDM studies were mostly aimed at prediction from data mining tasks. One of the results of this study is that artificial neural networks are the most commonly used technique in EDM studies. When the distributions of EDM studies according to their objectives are examined, it is seen that studies are predominantly aimed at predicting student achievement. It is seen that university students are preferred as the sample in EDM studies, achievement scores are used as data source and SPSS application is used more as an analysis tool. In the last part of the research, recommendations were made based on the results to the researchers.

Concept and knowledge maps are used often in learning process as two dimensional learning materials. These maps are important in comprehending concepts of a subject and relationships between these concepts. Nowadays, concept maps can be used beyond student drawings as digital navigation tools in real life. The aim of this study is to investigate the impact of the use of digital concept maps as navigation tools in online learning environments on student success and disorientation. There are two subdimensions of the navigation tool: the concept map and the content tree. The achievement test designed by the researcher in order to determine success of the student is used in the research. To evaluate the level of the student’s disorientation, the disorientation scale and navigation data were used in hypermedia. Web navigation data were recorded in the database, while participants were doing their weekly tasks, and Needleman-Wunsch algorithm was used to determine the level of disorientation. As a result of the study, the success of students in both groups has a significant increase positively. Besides, students who used websites with a content tree are more successful than students who used websites with concept maps. There is not a significant difference in the perception of disorientation between groups according to the navigation tool that they used. Nevertheless, according to the results of analyses that are made with using web navigation data, it is seen that there is a difference in disorientation of students, considering the number of subjects or concepts in the navigation tool, the content of the task that has been given etc. Lastly, suggestions about what to pay attention to while using concept maps or concept maps in online learning sites have been given.

Student modeling is one of the most important processes in adaptive systems. Although learning is individual, a model can be created based on patterns in student behavior. Since a student model can be created for more than one student, the use of machine learning techniques in student modeling is increasing. Artificial neural networks (ANNs), which form one group of machine learning techniques, are among the methods most frequently used in learning environments. Convolutional neural networks (CNNs), which are specific types of these networks, are used effectively for complex problems such as image processing, computer vision and speech recognition. In this study, a student model was created using a CNN due to the complexity of the learning process, and the performance of the model was examined. The student modeling technique used was named LearnerPrints. The navigation data of the students in a learning management system were used to construct the model. Training and test data were used to analyze the performance of the model. The classification results showed that CNNs can be used effectively for student modeling. The modeling was based on the students’ achievement and used the students’ data from the learning management system. The study found that the LearnerPrints technique classified students with an accuracy of over 80%.

This study suggests a classification model and an e-learning system based on this model for all instructional theories, approaches, models, strategies, methods, and technics being used in the process of instructional design that constitutes a direct or indirect resource for educational technology based on the theory of intuitionistic fuzzy sets (IFS). IFS is a set theory through expanding the membership systems of the classic theory of fuzzy sets in such a way to also involve the indeterminacies. As the model is grounded on a mathematical base, it also presents a convenient platform to define various metrics.