Digital Text Forensics and Stylometry

PAN, a series of workshops and challenges, is dedicated to advancing the fields of digital text forensics and stylometry. Every year, PAN presents a set of well-defined tasks designed for competitive evaluation. These tasks typically encompass various facets of text analysis, including authorship verification (e.g., given two texts belonging to different Discourse Types (DT), determine if they are written by the same author?) or attributing authorship to generative AI models (given two texts, one authored by a human, one by a machine: pick out the human?). For each task, PAN furnishes participants with curated datasets and baseline models. If you are interested in working on any of these tasks in your master thesis, contact us.