Abstract:
Sociolinguistics is described as "the study of how language and social factors such as ethnicity, social class, age, gender, and educational level are related". Social factors may result in differences in language use, which may then be referred to as sociolinguistic differences. The goal of this project is to answer the following question: is it possible to identify sociolinguistic differences in the way people use programming languages? How might we go about answering our question? We propose that techniques from corpus linguistics may be of use. Computer-based techniques such as text mining allow the use of software in the identification of trends in language use that would otherwise require an enormous amount of human effort to discover. Once various sociolinguistic differences have been identified by computational means, traditional critical analysis methods can then be applied for further analysis.
PPIG 2014 - 25th Annual Workshop
Linking Linguistics and Programming: How to start? (Work in Progress)