The problem of studying the cluster structure of a set of objects with qualitative (categorical) features is considered. We propose an approach to visualization of source data and categorical data groups in a form that is convenient for human analysis and decision-making. We generalized Andrews’ idea of numeric data visualization for the case of categorical data set. The developed approach can be applied in the case when the frequency distribution of the joint appearance of feature pairs in the data sample is known. For visualization, it is proposed to use not the primary features of the data set, but new paired features that have a strong statistical relationship. In addition, we have corrected the spectral representation of Andrews curves, limiting the maximum frequency of harmonic functions. The proposed visual representation of categorical data makes it possible to estimate the number of clusters in a data set and show their differences. The technique is demonstrated on a model example in which the decision on the number of clusters is taken in conjunction with two other ways of visualizing data clusters: a silhouette and a heat map.

A weak semantic map, as opposed to a strong semantic map, allows for a choice of coordinates that are characterized by definite semantics: e.g., valence, arousal, dominance. Weak semantic maps of words can be built from synonym-antonym dictionaries, by pulling synonyms together and antonyms apart. Polysemy is one of the problems with this approach. Indeed, typically one and the same word has multiple meanings, while it has to be represented by only one point on the map. To solve this problem, it seems natural to use word senses rather than words as the map elements. In this work, we consider a semantic map of word senses built from the thesaurus of Microsoft Word for the Russian language. To determine senses of words with the purpose of its further representation on the built map of word senses is developing a method, the result of which is presented in this article. The main conclusion is that semantic maps of word senses have an advantage over semantic maps of words, since they allow for a context-specific evaluation of word meaning. This approach removes the restriction caused by polysemy - the multiplicity of senses of one word.