Natural Language Processing (NLP) has changed radically with the emergence of neural network approaches that learn to represent words, sentences, and other linguistic units as dense real-valued vectors, so-called embeddings. In this talk, I will give an introduction to word embeddings: what are they, how can we use them to explore social science questions, and what are potential pitfalls? I will highlight two case studies: one on societal biases, and one on language change on Twitter.

Dr. Dong Nguyen is an assistant professor at the department of Information and Computing Sciences at Utrecht University (NL). She is interested in developing NLP methods to explore social science questions. At Utrecht she leads the NLP and Society Lab. Her other research interests include explaining and communicating NLP and computational sociolinguistics.