This paper presents an approach that uses probabilistic logic reasoning to compute subjective interestingness scores for classification rules. In the proposed approach, domain knowledge is represented as a probabilistic logic program that encodes information from experts and statistical reports. The computation of interestingness scores is performed by a procedure that applies linear programming to reasoning regarding the probabilities of interest. It provides a mechanism to calculate probability-based subjective interestingness scores. Further, a sample application illustrates the use of the described approach.