Demographic Dialectal Variation in Social Media: A Case Study of African-American English
This work addresses the problem of NLP tool bias for dialectal language, specifically for African-American English on social media, which is incremental as it builds on existing linguistic studies with new data and methods.
The study tackled the lack of NLP resources for dialectal language on social media by analyzing African-American English (AAE) on Twitter, resulting in a distantly supervised model for identification, a new corpus, and an ensemble classifier that eliminated performance disparities in language identification tools.
Though dialectal language is increasingly abundant on social media, few resources exist for developing NLP tools to handle such language. We conduct a case study of dialectal language in online conversational text by investigating African-American English (AAE) on Twitter. We propose a distantly supervised model to identify AAE-like language from demographics associated with geo-located messages, and we verify that this language follows well-known AAE linguistic phenomena. In addition, we analyze the quality of existing language identification and dependency parsing tools on AAE-like text, demonstrating that they perform poorly on such text compared to text associated with white speakers. We also provide an ensemble classifier for language identification which eliminates this disparity and release a new corpus of tweets containing AAE-like language.