Demographic Dialectal Variation in Social Media: A Case Study of African-American English
Sociolinguistics
The short version
A study of African-American English in online conversation. The authors develop a model for identifying AAE-like language, examine its linguistic features, and show that existing language-identification and parsing tools perform unevenly across language varieties.
Notes for the reading desk
- Language variation matters when evaluating computational tools.
- A model’s errors may reflect the varieties represented in its training data.
- Demographic associations in a corpus are not individual identity determinations.
Citation
Blodgett, S. L., Green, L., & O’Connor, B. (2016). Demographic Dialectal Variation in Social Media: A Case Study of African-American English. Proceedings of EMNLP, 1119–1130. https://doi.org/10.18653/v1/D16-1120
Summary and reading notes are editorial guides. The linked paper is the original source.