Özet:

COVID-19, a new virus, has been caused an outbreak in all around the world. It has affected almost all parts of our lives such as working habits. The life of human beings has come to a halt. People have started to work in their homes. Besides, education activities from preschool to the colleges have canceled and distance courses took place instead of face to face education. This situation has caused fear and anxiety. Especially for students, the anxiety level about education has increased during the pandemic. In this study, the relationship of the students’ academic level and gender with Covid-19 based anxiety and protective behaviors is investigated based on the data mining approach. To this end, an association rule-based classification (ARC) method is employed. Moreover, other classification approaches namely decision trees (DT), support vector machines (SVM) and k-nearest neighbor (k-NN) are also used. The ARC is used to detect the association rules between items of the dataset and obtained rules are used to construct a classifier. To detect the relationships between the students’ academic level and gender with COVID-19 based anxiety and protective behaviors, a dataset, which was constructed from 215 university students by using an online self-administered questionnaire, is considered in experimental studies. The dataset covers three instruments namely Anxiety Scale (AS) with 10 items, Protective Behaviors Scale (PBS) with 14 items, and Related Knowledge Scale (RKS) with 12 items, respectively. The experimental results show that the proposed data mining approaches produce satisfactory results in determining the relationship between the students’ academic level and gender with Covid-19 based anxiety and protective behaviors.

Anahtar Kelimeler: