Nathan Dykes

I am a linguist working in the Computing Text and Language group at the Department of Digital Humanities and Social Studies, FAU Erlangen-Nürnberg. My research centres on corpus methodology with a strong interdisciplinary profile spanning computational linguistics and digital humanities. I focus on developing creative ways to retrieve linguistic phenomena that resist straightforward operationalisation. In other words: what patterns are hiding in corpora, and how can we find them reliably, transparently, and interpretably?

My PhD develops a methodological framework for corpus-based discourse analysis. Beyond discourse, my research has taken me into argumentation mining (with computer scientists), medical and legal language (with domain experts), and corpus construction and annotation work for social media and web data. More recently, I’ve been working on concordance-based approaches to literary stylistics in the Reading concordances in the 21st century (RC21) project, and my current interests are expanding towards pragmatics. I bring a background in computational linguistics and have programming experience in Python and R.