Those lemmata whose frequency in the relevant poem is statistically significantly higher than their frequency in the entire Corpus of Czech Verse. Statistical significance is further verified by the χ2 test with Yates correction and the log-likelihood test. The user is able to specify whether the tests would be applied at α = 0.001 or α = 0.01 levels. At the same time, the user can specify which word class ought to be left out of the keyword analysis (at the initial level, only nouns, adjectives and verbs are permitted), and determine the minimum number of occurrences of the lemma in the poem for the lemma to be included among keywords.
Person responsible for administration of information source:
Petr Plecháč (email@example.com)
Author/administrator of source:
Institute of Czech Literature of the CAS, v. v. i.
Type of resource: