Authorship clustering using multi-headed recurrent neural networks

2016/08/16 by Douglas Bagnall, Bagnall, Douglas · 1 citation
Computer Science · #Authorship Attribution and Profiling #Computation and Language (cs.CL) #FOS: Computer and information sciences #Spam and Phishing Detection #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1608.04485

openalex publication_date 2016/08/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

A recurrent neural network that has been trained to separately model the language of several documents by unknown authors is used to measure similarity between the documents. It is able to find clues of common authorship even when the documents are very short and about disparate topics. While it is easy to make statistically significant predictions regarding authorship, it is difficult to group documents into definite clusters with high accuracy.

Citations

• Finding Structure in Time

Cited by

• Better Call Claude: Can LLMs Detect Changes of Writing Style?

Related

• Author Identification using Multi-headed Recurrent Neural Networks
• Experiments with Neural Networks for Small and Large Scale Authorship Verification
• Authorship Attribution Using Word Network Features
• Authorship Attribution Using a Neural Network Language Model
• Unsupervised authorship attribution