LLM-Models for Multi-Author Writing Style Analysis

Thesis Type Bachelor
Thesis Status
Currently running
Student Daniel Rufinatscha
Thesis Supervisor
Research Field

The goal of multi-author writing style analysis is to investigate methods to scrutinize the unique writing styles of different authors. This task serves as a crucial precursor to tasks such as identifying changes in authorship within a text or determining the author of a given piece of writing, known as authorship attribution. DBIS is one of the organizers of the multi-author writing style analysis task at the PAN shared tasks on digital text forensics and stylometry, aiming to advance the field of multi-author writing style analysis. The goal of this bachelor thesis is to implement a set of LLM-based baseline approaches for the task and to deploy them on the TIRA platform