Now We Stronger than Ever: African-American English Syntax in Twitter

By Ian Stewart. 2014

20 citations recorded by the source corpus.

African American English (AAE) is a well-established dialect that exhibits a distinctive syntax, including constructions like habitual be . Using data mined from the social media service Twitter, the proposed senior thesis project intends to study the demographic distribution of a sub-set of AAE syntactic constructions. This study expands on previous sociolinguistic Twitter work (Eisenstein et al., 2011) by adding part-of-speech tags to the data, thus enabling detection of short-range syntactic features. Through an analysis of ethnic and gender data associated with AAE tweets, this project will provide a more accurate description of the dialect’s speakers and distribution.

Subfields: Language and Linguistics, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Language and Linguistics

1. Su Lin Blodgett
2. Brendan T. O'Connor
3. Jacob Eisenstein
4. Alan W. Black
5. D. Sharma
6. Johnny Tian-Zheng Wei
7. Shrimai Prabhumoye
8. Anthony Rios

In Human-Computer Interaction

1. Jacob Eisenstein
2. Brendan T. O'Connor
3. Alan W. Black
4. Vinodkumar Prabhakaran
5. Su Lin Blodgett

Citations in the corpus

• Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English (2017, positive): “Our previous work [3] veri€es that its African-American language model learns linguistic aŠributes known in the sociolinguistics literature to be characteristic of AAE, in line with other work that has also veri€ed the correspondence of geographical AA prevalence to AAE linguistic features on TwiŠer”
• Learning to Recognize Dialect Features (2020, background): “In social media, features of African American Vernacular English (AAVE) can be identified by correlating linguistic frequencies with the aggregate demographic statistics of the geographical areas from which geotagged social media was posted (Eisenstein et al., 2011; Stewart, 2014; Blodgett et al., 2”
• Twitter Universal Dependency Parsing for African-American and Mainstream American English (2018, background): “Additionally, it contains an abundance of dialectal language, including African-American English (AAE), a dialect of American English spoken by millions of individuals, which contains lexical, phonological, and syntactic features not present in MAE (Green, 2002; Stewart, 2014; Jones, 2015).”
• Equity Beyond Bias in Language Technologies for Education (2019, background): “Systems today may also fail to recognize speech from students speaking certain dialects or accents, though progress in recognition for marginalized language variation is improving rapidly (Blodgett et al., 2016; Stewart, 2014; Jørgensen et al., 2015).”