Emotion-Aware Clickbait Attack in Social Media

2026-04-29

AI Summary

This study addresses the limitations of existing clickbait detection systems, which predominantly rely on superficial linguistic features and struggle to counter emerging attacks that exploit emotional manipulation. To bridge this gap, the work introduces emotion dynamics modeling into clickbait generation for the first time, proposing an emotion-aware adversarial attack framework. Leveraging the Valence-Arousal-Dominance (VAD) emotion space, the method integrates Sentence-BERT for semantic alignment and large language models for stylistic rewriting to construct an emotion-driven curiosity-gap mechanism. This mechanism quantifies how emotional arousal influences user engagement and evasion of detection. Experimental results demonstrate that the proposed approach significantly increases the false-negative rate of state-of-the-art detectors from 2.58% to 30.63%, effectively exposing their vulnerability to emotionally manipulative adversarial examples.

Abstract

Clickbait is characterized by disproportionately high emotional intensity relative to informational content, often reinforced by specific structural patterns. However, current research considers clickbait as a static textual phenomenon characterized by linguistic patterns and structural cues. Additionally, existing detection systems primarily rely on surface-level features of clickbait. This paper introduces an emotion-aware clickbait generation attack, where stylistic transformations are used to optimize emotional impact. We propose an emotion-aware framework based on the Valence-Arousal-Dominance (VAD) space to model the emotional dynamics underlying clickbait generation for optimal user engagement. To simulate realistic attack scenarios, we align clickbait headlines with semantically similar social media posts using Sentence-BERT and generate multiple stylistic rewrites via Large Language Models (LLMs). Building on this, we define a Curiosity Gap (CG) function that computes clickbait's headline variation to the current post to quantify how emotional activation will contribute to user curiosity and evade the existing system found on social media. Experimental results demonstrate that emotion-aware stylization significantly degrades the performance of state-of-the-art classifiers, leading to misclassification rates of up to 2.58% to 30.63% on the base system.

Problem

• clickbait
• emotion-aware
• social media
• adversarial attack
• user engagement

Innovation

• emotion-aware
• clickbait generation
• Valence-Arousal-Dominance (VAD)
• Curiosity Gap
• Large Language Models (LLMs)