Cross-Domain Authorship Verification Based on Topic Agnostic Features

Authorship verification (AV) is a research branch in digital text forensics that deals with the problem to determine whether two documents were written by the same author. Research activities in the context of AV have steadily increased in recent years, which have led to a variety of approaches trying to solve this problem. Many of these approaches, however, make use of features that are related to or influenced by the topic of the documents. Therefore, it may accidentally happen that their verification results are based not on the writing style alone (the actual focus of AV), but on the topic of the documents. To address this problem, we propose in the context of the AV shared task at the PAN 2020 workshop an alternative approach, which considers only topic-agnostic features in its classification decision. On the official test set, our approach was ranked third out of all submitted approaches.