SLIDE 12 Young Linguists' Seminar, 16 April 2015 12
FORM / AUTHOR NUMBER OF OCCURRENCES / CORPUS FACTORS (ID-TAGS) STATISTICAL TECHNIQUES run (v) / Gries (2006) 815 / the ICE-GB and the Brown Corpus
morphological: verb tense, aspect and voice syntactic: intransitive, transitive, complex transitive verb form; main clause, subordinate clause semantic: subjects, objects and complements – human, animate, concrete countable, concrete mass, machines, abstract entities,
- rganizations/institutions,
locations, quantities, events, processes collocates senses
Hierarchical agglomerative cluster analysis run (v) / Glynn (2014a) 500 / the BNC, the ANC and the LiveJournal Corpus The same as in Gries (2006) PLUS dialect: BrE, AmE register: conversation, blog Hierarchical agglomerative cluster analysis Chi-squared tests Binary correspondence analysis Multiple correspondence analysis Logistic regression