Dataset and R Code for "Semantic Ambiguity of High-Frequency Polysemous Verbs in Business English: A Corpus-Based Investigation

This record contains the analysis materials for a corpus-based study of sense disambiguation in four high-frequency polysemous verbs in Business English: run, execute, bear, and discharge. It includes the R script used for sense coding and statistical testing, the collocate frequency tables for the Business and General sub-corpora, and the contingency tables underlying the chi-square and Cramér's V analyses. Data were derived from 36,219 KWIC instances retrieved from the Corpus of Contemporary American English (COCA), with 15,841 instances in the Business sub-corpus and 20,378 in the General sub-corpus. Only derived frequency data and analysis code are distributed here; full corpus text is not redistributed, in accordance with the terms of use of the source corpus.