Profiling verb complementation constructions across New Englishes A two-step random forests analysis of ing vs. to complements

In this paper, we explore verb complementation patterns with to and ing in native English (British and American English) as compared to three Asian Englishes (Hong Kong, Indian, and Singaporean English). Based on data from the International Corpus of English annotated for variables describing the matrix verb and the complement, we run two random forests analyses to determine where the Asian Englishes have developed complementation preferences different from the two native speaker varieties. We find not only a variety of differences between the Asian and the native Englishes, but also that the Asian Englishes are more similar (i.e. 'better predicted by') the American English data. Further, as the first study of its kind to extend the MuPDAR approach from the now frequent regression analyses to random forests analysis, this study adds a potentially useful analytical tool to the often messy and skewed observational data corpus linguists need to deal with.