Authorship Verification
Authorship verification aims to determine if two text samples share the same author, a task with applications in forensics, plagiarism detection, and online security. Current research focuses on improving accuracy and explainability using large language models (LLMs), ensemble learning methods, and novel approaches like contrastive learning and self-supervised learning, often incorporating stylistic features and addressing challenges like topic leakage and adversarial attacks. These advancements are significant for enhancing the reliability and interpretability of authorship analysis across diverse text types, including code, handwritten documents, and online communications.
Papers
The Semantic Scholar Open Data Platform
Rodney Kinney, Chloe Anastasiades, Russell Authur, Iz Beltagy, Jonathan Bragg, Alexandra Buraczynski, Isabel Cachola, Stefan Candra, Yoganand Chandrasekhar, Arman Cohan, Miles Crawford, Doug Downey, Jason Dunkelberger, Oren Etzioni, Rob Evans, Sergey Feldman, Joseph Gorney, David Graham, Fangzhou Hu, Regan Huff, Daniel King, Sebastian Kohlmeier, Bailey Kuehl, Michael Langan, Daniel Lin, Haokun Liu, Kyle Lo, Jaron Lochner, Kelsey MacMillan, Tyler Murray, Chris Newell, Smita Rao, Shaurya Rohatgi, Paul Sayre, Zejiang Shen, Amanpreet Singh, Luca Soldaini, Shivashankar Subramanian, Amber Tanaka, Alex D. Wade, Linda Wagner, Lucy Lu Wang, Chris Wilhelm, Caroline Wu, Jiangjiang Yang, Angele Zamarron, Madeleine Van Zuylen, Daniel S. Weld
Same or Different? Diff-Vectors for Authorship Analysis
Silvia Corbara, Alejandro Moreo, Fabrizio Sebastiani