This study explores the linguistic application of bipartite spectral graph partitioning, a graphtheoretic technique that simultaneously identifies clusters of similar localities as well as clusters of features characteristic of those localities. We compare the results using this approach to previously published results on the same dataset using cluster and principal component analysis (Shackleton, 2007). While the results of the spectral partitioning method and Shackleton's approach overlap to a broad extent, the analyses offer complementary insights into the data. The traditional cluster analysis detects some clusters which are not identified by the spectral partitioning analysis, while the reverse also occurs. Similarly, the principal component analysis and the spectral partitioning analysis detect many overlapping, but also some different linguistic variants. The main benefit of the bipartite spectral graph partitioning method over the alternative approaches remains its ability to simultaneously identify sensible geographical clusters of localities with their corresponding linguistic features.

This study applies quantitative techniques—measures of linguistic distance, cluster analysis, principal components analysis, and regression analysis—to data on English speech variants in England and America. The analysis yields measures of similarity among English and American speakers, distinguishes clusters of speakers with similar speech patterns, and isolates groups of variants that distinguish those groups of speakers. The results are consistent with a model of new-dialect formation in the American colonies, involving competition within and selection from a pool of variants introduced by speakers from different dialect regions. The patterns of similarity appear to be largely consistent with the historical evidence of migrations from seventeenth- and eighteenth-century Britain to North America, lending support to the hypothesis of regional English origins for some important differences in American dialects, and suggesting mainly southeastern English influence on American speech, with somewhat greater southeastern influence on New England speech and southwestern influence in the American South.

This study explores the linguistic application of bipartite spectral graph partitioning, a graph-theoretic technique that simultaneously identifies clusters of similar localities as well as clusters of features characteristic of those localities. We compare the results using this approach to previously published results on the same dataset using cluster and principal component analysis (Shackleton, 2007). While the results of the spectral partitioning method and Shackleton's approach overlap to a broad extent, the analyses offer complementary insights into the data. The traditional cluster analysis detects some clusters which are not identified by the spectral partitioning analysis, while the reverse also occurs. Similarly, the principal component analysis and the spectral partitioning analysis detect many overlapping, but also some different linguistic variants. The main benefit of the bipartite spectral graph partitioning method over the alternative approaches remains its ability to simultaneously identify sensible geographical clusters of localities with their corresponding linguistic features.