Are We All in a Truman Show? Spotting Instagram Crowdturfing through Self-Training

TL;DR

This paper introduces the first Instagram crowdturfing detection method using semi-supervised learning, achieving high accuracy and revealing significant artificial engagement among mega-influencers, highlighting the challenge of content-based detection.

Contribution

It presents a novel semi-supervised approach for detecting crowdturfing on Instagram, leveraging profile features and outperforming supervised methods in identifying fake engagement.

Findings

Achieved 95% F1-score in detecting crowdturfing profiles.

Discovered over 20% of engagement on mega-influencers is artificial.

Content analysis alone is insufficient for detecting crowdturfing activities.

Abstract

Influencer Marketing generated $16 billion in 2022. Usually, the more popular influencers are paid more for their collaborations. Thus, many services were created to boost profiles' popularity metrics through bots or fake accounts. However, real people recently started participating in such boosting activities using their real accounts for monetary rewards, generating ungenuine content that is extremely difficult to detect. To date, no works have attempted to detect this new phenomenon, known as crowdturfing (CT), on Instagram. In this work, we propose the first Instagram CT engagement detector. Our algorithm leverages profiles' characteristics through semi-supervised learning to spot accounts involved in CT activities. Compared to the supervised approaches used so far to identify fake accounts, semi-supervised models can exploit huge quantities of unlabeled data to increase performance. We purchased and studied 1293 CT profiles from 11 providers to build our self-training classifier, which reached 95\% F1-score. We tested our model in the wild by detecting and analyzing CT engagement from 20 mega-influencers (i.e., with more than one million followers), and discovered that more than 20% was artificial. We analyzed the CT profiles and comments, showing that it is difficult to detect these activities based solely on their generated content.