Qualitative analysis in laser-induced breakdown spectroscopy (LIBS) encompasses various techniques for classifying and clustering spectral data without quantifying the sample composition. This approach is particularly useful in LIBS due to its ability to collect large amounts of data with minimal sample preparation, making it ideal for quickly grouping similar materials together. This chapter serves as a dictionary between the “languages” used in LIBS and fields dedicated to data processing. A major emphasis is put on the introduction of terminology and notation necessary to allow one to conduct a more extensive self-study based on more rigorous and complete literature sources. A detailed review of specific applications of qualitative analysis in LIBS is not included, but relevant review articles are referenced. The discussed classification techniques are logistic regression, decision trees, ensemble models, support vector machines, and artificial neural networks. The presented clustering techniques are the k-means clustering algorithm, hierarchical clustering, and density-based spatial clustering of applications with noise. Each technique (classification and clustering) is demonstrated on a real but simplified LIBS dataset of geological targets. Introductory Python code is included.