Software requirements are constantly changing. Consequently, the development process is frequently under time pressure, which results in technical debt. To illustrate the symptoms of technical debt, 22 code smells have been introduced to indicate the poor design in code fragment, among which refused bequest is one of the most harmful smells and with high diffuseness. However, refused bequest is rarely taken into account because there is a lack of dataset. Moreover, it is difficult to design the detection rules for refused bequest compared with other popular smells.In this paper, we propose a machine-learning-based refused bequest smell detection framework SEADART, which features the utilization of a set of synthetic smelly instances. Specifically, SEADART comprises three components: (1) a smell generation approach, and (2) a model training strategy, and (3) an AdaBoost-based detection model. We evaluate the performance of the proposed framework. The evaluation results suggest that the generated smelly instances are reliable, and the trained AdaBoost model significantly outperforms the state-of-the-art over a real-world dataset.