Find correlations between (numeric) variables in a dataset.
Interpret the underlying (theoretically-relevant) dimensions in the dataset.
Describe groups of texts based on these dimensions.
In register analysis
Biber (1988) finds 7 underlying dimensions to 69 variables and describes textual registers based on them.
E.g. Narrative emphasis (past tense, 3PP, perfect aspect, public verbs … against adjectives, present tense.)
Can we identify interpretable dimensions of register variation on the basis of the data and what are the relationships between the metaregisters, as well as more specific subsections, with regard to these dimensions?
He showed convincingly that anxiety is a learned ( conditioned ) reaction and is the basis of experimental and clinical neuroses and assumed , therefore , that the neuronal changes which underlie the neuroses are functional and reversible .
Left
short words, punctuation POS bigrams, pronouns adverbs
nominalizations, nouns, adjectives
Through which he has granted us the very great and precious promises , so that through them you may become partaker of the divine nature .
Representative files for Factor 2
Pole
Preferred
Dispreferred
Random example
Right
short words, composite expressions, negations, punctuation, personal pronouns, adverbs
nouns and adjectives
You ought to know that ’’ .
Left
long words, nouns and adjectives
composite expressions, negations, punctuation, personal pronouns, adverbs
Most of us would say that in this delight at the killing of others or the causing of suffering there is something very unfitting .
Levshina, Natalia. 2015. How to Do Linguistics with R: Data Exploration and Statistical Analysis. Amsterdam; Philadelphia: John Benjamins Publishing Company.