T-IFS: Authorship Attribution for Social Media Forensics

We are glad to announce that our paper entitled “Authorship Attribution for Social Media Forensics” has been accepted at the IEEE Transactions on Information Forensics and Security (T-IFS), Volume PP Issue 99, 2016.

The goal of the presented research work is to identify authors of texts through features derived from the style of their writing with social media channels. The presented technique explores peculiarities of habit that influence the form and content of how people write in popular services like Twitter.

In addition, the authors also present a detailed walk-through of supervised learning methods for authorship attribution for social media forensics and a discussion of open problems in forensic authorship attribution.

Dataset and source-code.


Computational pipeline, in which features are extracted from very small samples of text, and scalable supervised learning is deployed to train author-specific models and make predictions about unknown samples

This entry was posted in blog, publications, science and tagged , , , , , , , , , , , . Bookmark the permalink.

1 Response to T-IFS: Authorship Attribution for Social Media Forensics

  1. Pingback: Talks: LIRMM and WIFS 2017, France | RECOD — Reasoning for Complex Data

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s