Impression Zombies: Characteristics Analysis and Classification of New Harmful Accounts on Social Media

TL;DR

This paper analyzes the behavioral patterns of 'Impression Zombies', malicious social media accounts that inflate engagement, and introduces a detection model achieving 92% accuracy to improve platform transparency.

Contribution

It provides the first quantitative characterization of Impression Zombies and develops a novel detection method based on contextual incoherence.

Findings

Impression Zombies post over three times more daily posts than average users.

They tend to use phrases like 'follow back' to gather followers.

The detection model achieved approximately 92% accuracy.

Abstract

``Impression Zombies'', a type of malicious account designed to artificially inflate engagement metrics, have recently emerged as a significant threat on X (formerly Twitter). These accounts disseminate a high volume of low-quality, irrelevant posts, which degrade the user experience. This study aims (1) to quantitatively characterize their behavioral patterns and (2) to develop a method for detecting such accounts. To address the first objective, we collected data from 9,909 accounts and compared the characteristics of Impression Zombies and general users within this dataset. We find that, Impression Zombies post more than three times the average total number of posts per day and tend to gather followers by using phrases such as ``follow back.'' Addressing the second objective, we constructed a classification model for Impression Zombies that leverages the contextual incoherence often observed between parent posts and the replies from Impression Zombies. Experimental results show that our model achieved approximately 92\% accuracy in detecting Impression Zombies. This study provides the first quantitative insights into Impression Zombies and offers a practical framework for detecting such accounts, contributing to platform transparency and the health of social media ecosystems.