Code smells are symptoms of poor implementation choices applied during software evolution. While previous research has devoted a notable effort in the definition of automated solutions to detect them in source code, still little is known on how to support developers when prioritizing them. Some works attempted to deliver solutions that can rank smell instances based on their severity, computed on the basis of software metrics. However, this may not be enough since it has been shown that the recommendations provided by current approaches do not take the developer’s perception of design issues into account. In this paper, we perform a first step toward the concept of emph{developer-driven} code smell prioritization and propose a machine learner able to rank code smells according to the perceived criticality that developers assign to them. We test our technique in an empirical study to investigate its accuracy but also the features that are more relevant for classifying the developer’s perception. Finally, we compare our approach with a state-of-the-art technique. Key findings show that the devised solution has an F-Measure up to 85% and outperforms the baseline approach.