An individual may sometimes feel anxious when a critical event happens. Job interview, wedding, moving in a new city/country can result this occurrence. Examinations taken in school are also that kind of events. Since our handwriting is controlled by brain, it is possible to see clear changes in handwriting style during examinations. In our study, an expert system is developed which considers handwriting features to predict student's exam anxiety state. 210 handwriting samples are collected and classification is made by using J48 decision tree algorithm. The average of Precision, Recall and F-Measure metrics are 71%, 66% and 67%, respectively.