The proliferation of social media platforms and users has provided sociolinguists a valuable resource at exploring linguistic variation and change at scale. While traditional variationist sociolinguistic rely on select linguistic variables to compare linguistic systems (a bottom-up approach), methods from Natural Language Processing (NLP) offer sociolinguists a unique top-down perspective in determining linguistic variation and change between linguistic systems. In this talk, I will discuss the challenges and opportunities of using NLP to complement existing approaches in computational sociolinguistics as it applies to social media language data.