Cross-validation revealed accuracy rates of 84.5% for /r/ and 91.8% for /t/.
Voiceless), using over 4,000 previously hand-coded tokens (per variable). Absent) and intervocalic medial /t/ (Voiced vs. Villarreal et al. (2020) trained random forest classifiers of two sociolinguistic variables of New Zealand English, non-prevocalic /r/ (varying between Present vs. 2021 McLarty, Jones & Hall 2019 Villarreal et al. In this talk, I discuss the advantages and challenges of using sociolinguistic auto-coding (SLAC), a method in which machine learning classifiers assign variants to variable data (Kendall et al. 2017), and accurate vowel measurement (e.g., Barreda 2021). Researchers in sociophonetics and variationist sociolinguistics have increasingly turned to computational methods to automate time-consuming research tasks such as data extraction (e.g., Fromont & Hay 2012), phonetic alignment (e.g., McAuliffe et al. Sociolinguistic auto-coding: Applications and pitfalls If you are interested in joining this talk, please contact Yongqing Ye or Suzanne Wagner for the Zoom link. Villarreal is also giving a talk to the SoConDi group at University of Michigan on Nov 4th, 2022, 3-4pm.
0 kommentar(er)
