Instagram bots and people who use specific services for likes, comments and followers purchase are identified as Suspicious Accounts.
At HypeAuditor, a machine learning process is implemented to identify suspicious accounts. The algorithm's classification is based on a decision tree; its error rate doesn't exceed 3.7% per test sample of 10,000 analyzed accounts.
The main features used in the algorithm are the following:
Followers/followings numbers and ratio
Number of posts
Account privacy
Registration date
Geotags usage
Additional proprietary signals
The decision tree model and the selection of specific features are based on the Influencer Marketing industry expertise. These signals also contribute to the Audience Quality Score (AQS), the overall benchmark for influencer audience quality in HypeAuditor reports.
Below are the most common examples of suspicious accounts:
