Lexicometry is the alliance of linguistics, mathematics and computer science. It processes large sets of texts (corpus), establishing their vocabulary, classifying the words types in terms of their frequency, their distribution, their grammatical categories. It establishes the contexts of a word type and the most frequent combinations in which it appears. These collocations are used to determine the meanings of the terms. Lexicometry also highlights the main themes of a corpus, its gender and style. It segments the corpus according to the main thematic and stylistic discontinuities. To obtain these results, some pre-processing is necessary: text labeling, correction and standardization of spellings, lemmatization. Then the text can be placed into an electronic library available to researchers.
