Educational Data Mining Patterns K-anonymity for The Analytics of Student Privacy Data

Along with the times and rapid technological advances, some methods can collect, store, and analyze data with extraordinary capabilities. More recently, academic institutions have also offered open and distance learning programs. Through these efforts, they obtain big data related to information and communication systems that involve their students by combining various modern big data analytical tools and techniques to maintain student data privacy. The main purpose of this research is to test analytical opportunities against a learning method while paying attention and protecting the security of student data. We can achieve balance in our data mining efforts to secure data privacy through the K-anonymization method. The results of this study indicate that, in testing the correlation coefficient on each online activity forum and student achievement scores, the most significant result was 0.298 on the "Total Log" activity platform. After the anonymization process, it is found that the decrease in the number of coefficients must be balanced with a significant enough loss of information.