A survey and reflection on the latest research breakthroughs in LLM-generated Text detection, including data, detectors, metrics, current issues and future directions.

Collected solutions from Google Code Jam programming competition (2008-2020).

project implementation and codes for finding who wrote the given texts (using NLP)

🌐 Identifying & Linking Vendor Migrants and Aliases on Darknet Markets. (ACL 2023)

Official FIRE 2020 Authorship Identification of SOurce COde (AI-SOCO) task repository containing dataset, evaluation tools and baselines

Authorship Attribution in Social Media & Chat Biometrics & Behavioral Biometrics

Authorship Identification for Reuters C50-50 dataset. Comparision between LSTM, GRU, Bi-LSTM models and also highlights use of 50 different stylometry features for classification.

A tool that predicts the dialect of English of an SMS message using recurrent neural networks supplemented with data from Google Trends.

Usage of stylometry and machine learning in computer forensics - real tools used in 2019 by the polish police. Everything in/for polish language.

Using Natural Language Processing to determine the author of an unlabeled text.

Курсовая работа по обработке данных

Bayesian analysis to determine the authorship of the disputed Federalist Papers

Topic-agnostic authorship tasks for Spanish political speeches

Mini Projecto 2

Code repository for the Multatuli project of the course Digital Humanities at the Vrije Universiteit Amsterdam (2021). Contributors: Alessandra Polimeno and Myrthe Buckens

Solving the Author Problem of “Dream of the Red Chamber” with the Writing Style Indicator以文風指標分析《紅樓夢》的作者爭議問題