In practical applications of data-driven Structural Health Monitoring (SHM), recording labels for each of the measured signals can be infeasible and expensive. In consequence, conventional methods for (supervised) machine learning can become irrelevant in certain applications of damage classification. Semi-supervised methods, however, allow algorithms to learn from information in the available unlabelled measurements as well a limited set of labelled data. As such, this paper suggests a semi-supervised Gaussian mixture model for probabilistic damage-classification, informed by both labelled and unlabelled signals. The generative statistical model is shown to improve the classification performance, compared to supervised learning, with simulated and experimental SHM data, while requiring no further inspections of the system. Specifically, semi-supervised learning leads to 3.87% and 3.83% reductions in the classification error for the simulated and experimental datasets respectively. These results indicate that, through semi-supervised learning in SHM, the cost associated with labelling data could be managed, as the information in a small set of labelled signals can be combined with larger sets of unlabelled data.