The Hα spectral line is a well-studied absorption line revealing properties of the highly structured and dynamic solar chromosphere. The presented work is based on high-spectral resolution Hα spectra obtained with the echelle spectrograph of the Vacuum Tower Telescope (VTT) located at Observatorio del Teide (ODT), Tenerife, Spain. The number of spectra accumulated at VTT over one observing day easily reaches up to millions. Hence, we require tools to identify and classify spectra with minimal human intervention. I will present exploratory work, which provides the framework and some ideas on how to tailor a classification scheme towards specific spectral data and science questions. t-distributed Stochastic Neighbor Embedding (t-SNE) is a machine learning algorithm, which is used for nonlinear dimensionality reduction. In this application, it projects Hα spectra onto a two-dimensional map, where it becomes possible to classify the spectra according to results of Cloud Model (CM) inversions. The CM parameters optical depth, Doppler width, line-of-sight velocity, and source function describe properties of the cloud material. Initial results of t-SNE indicate its strong discriminatory power to separate quietSun and plage profiles from those that are suitable for CM inversions. Furthermore, I will discuss our choice of various t-SNE parameters, the impact of seeing on classification, the results arising from various types of input data, and the link of the identified clusters to chromospheric features. Although t-SNE proves to be efficient in clustering high-dimensional data, human inference is required at each step to interpret the results.