Development of Artificial Intelligence Supported Student Monitoring and Evaluation System for e-Learners

In the project, it is aimed to develop a monitoring and evaluation system based on learning analytics to increase student interaction and prevent possible failures in online learning environments. Within the scope of the project, a system has been developed that monitors the learning processes of students in the Moodle learning management system, makes predictions about their academic performance in the light of this data, and allows intervention to students at risk. Pilot conducted to test the effectiveness of the system Within the scope of familiarization, 1) the students' Moodle interactions before and after using the system, 2) their dropping out of the course, and 3) their views on the developed system were analyzed. The findings are as follows: In the case where the system is used, students; They performed more activities in the Moodle environment, the number of different days they visited Moodle increased, they participated more in the discussion environment, they participated more in quizzes, and they viewed the course content more. Three of the 64 students enrolled in the course in which the pilot study was conducted had never entered the Moodle environment of the course. Of the remaining 61 students, 59 (97%) actively used the system and took the final exam. Only two students (3%) dropped out of the course in the process. The artificial intelligence supported student monitoring and evaluation system developed within the scope of the project reports the information obtained as a result of the analysis of the data collected regarding the learning processes of the students with machine learning methods to the lecturer and students. Thanks to the developed tool, course supervisors; They can make detailed analyzes based on data about their distance education courses, monitor how actively students participate in these courses, identify students at risk in a timely manner, and plan the necessary interventions for these students to be successful in the course. Using this data, the system can automatically intervene to students at risk. It is predicted that the developed system will be effective in increasing the interaction of students in online courses and preventing possible failures.