Working with Language Data

Catalog description

This course offers hands-on experience in discovering, compiling, analyzing, and describing language data. We'll work on diverse spoken- and signed-language data in different modalities (text, audio, video) and communities (e.g., online and offline). We'll practice techniques such as identifying patterns from texts, e.g., keywords and topics, comparing different varieties of languages, and effectively using large language models. The tools we use include Python, but no prior experience in programming or statistics is required. We'll work with generic scripts that can be adapted to your research questions. This course will expand your toolkit in using data and technology to address language-related questions and enhance your ability to critically assess claims about objectivity, scale, and automation.