Stylometric Detection of AI-Generated Text in Twitter Timelines

TL;DR

This paper introduces a stylometric-based algorithm to detect AI-generated tweets and identify when AI starts generating content within Twitter timelines, addressing challenges posed by short text lengths.

Contribution

It proposes novel stylometric models for distinguishing human and AI tweets and detecting the onset of AI-generated content in timelines, improving detection accuracy.

Findings

Stylometric features effectively augment existing detectors.

Models successfully discriminate between human and AI tweets.

Detection of AI-generated content onset is feasible in Twitter timelines.

Abstract

Recent advancements in pre-trained language models have enabled convenient methods for generating human-like text at a large scale. Though these generation capabilities hold great potential for breakthrough applications, it can also be a tool for an adversary to generate misinformation. In particular, social media platforms like Twitter are highly susceptible to AI-generated misinformation. A potential threat scenario is when an adversary hijacks a credible user account and incorporates a natural language generator to generate misinformation. Such threats necessitate automated detectors for AI-generated tweets in a given user's Twitter timeline. However, tweets are inherently short, thus making it difficult for current state-of-the-art pre-trained language model-based detectors to accurately detect at what point the AI starts to generate tweets in a given Twitter timeline. In this paper, we present a novel algorithm using stylometric signals to aid detecting AI-generated tweets. We propose models corresponding to quantifying stylistic changes in human and AI tweets in two related tasks: Task 1 - discriminate between human and AI-generated tweets, and Task 2 - detect if and when an AI starts to generate tweets in a given Twitter timeline. Our extensive experiments demonstrate that the stylometric features are effective in augmenting the state-of-the-art AI-generated text detectors.