Organizational and psychological research increasingly uses language data to measure variables and test hypotheses in novel ways. This revolution has been brought on by the availability of open source tools for analyzing language data (e.g., speech, emails, earnings call transcripts, social media content). We will use Python to equip students with skills and example code for using a variety of natural language processing (NLP) methods for converting text data to quantitative data, including traditional, count-based approaches to NLP (dictionaries, n-grams), word embeddings (e.g., word2vec), document embeddings (e.g., BERT), and large language models (LLMs; e.g., GPT, Llama). We will learn how to use these NLP approaches: to estimate similarity among different entities, build predictive models for measuring constructs, to fine tune document embedding models and LLMs, and how to use LLMs to measure variables without training data. Overall, students will come away with a variety of tools for applying NLP in organizational research, while also learning about a variety of papers that have used NLP in organizational research, including micro and macro research and ranging from industrial psychology and human resources topics (e.g., selection and assessment) to organizational behavior/psychology topics.