Instagram: User networks cleverly trick algorithms with mutual interaction
Researchers at New York University have used a new machine learning tool to uncover hidden networks of Instagram users who manipulate the social media platform's algorithm and artificially inflate the popularity of content and accounts.
The members of these groups, also called “pods,” interact with each other and easily outsmart the social network.
“Networks difficult to recognize”
“Instagram Pods have been around for quite a long time, these groups talk to each other, give each other false popularity. The algorithm primarily highlights content with high interaction rates, which is why some users resort to such tricks.
If they are cleverly organized and do not act according to specific patterns, such networks are difficult for the algorithm to detect,”
says social media expert Felix Beilharz in the press release interview.
[mk_ad]
The research team used machine learning to analyze 1.8 billion Instagram posts from 111,455 different accounts. The experts not only discovered that Instagram pods not only increase the visibility of postings, but also trigger real, organic interactions with them.
Easy access to the pods
A total of 70 percent of Instagram users who joined pods experienced at least a doubling of interaction afterward. The pods discovered are networks with between 900 and 17,000 users. It is very easy to become part of these networks, only four percent of pods require a minimum number of followers.
“Most attempts to game the system involve automated techniques such as bots. Social media companies have become better at combating such attacks.
“Pods, on the other hand, are more difficult to detect because people in them operate manually,”
explains Janith Weerasinghe, co-author of the study.
However, with machine learning it is possible to develop tools that detect such manipulation.
Related to the topic: Network Enforcement Act: New rules for Facebook, Instagram and Co!
Source: press text
Article image: TZIDO SUN / Shutterstock
Notes:
1) This content reflects the current state of affairs at the time of publication. The reproduction of individual images, screenshots, embeds or video sequences serves to discuss the topic. 2) Individual contributions were created through the use of machine assistance and were carefully checked by the Mimikama editorial team before publication. ( Reason )