{"id":18370,"date":"2020-04-30T00:21:39","date_gmt":"2020-04-30T00:21:39","guid":{"rendered":"https:\/\/rbsitsoftwaresolution.com\/blog\/instagram-pods-game-the-algorithm-by-coordinating-likes-and-comments-on-millions-of-posts.html"},"modified":"2020-04-30T00:21:39","modified_gmt":"2020-04-30T00:21:39","slug":"instagram-pods-game-the-algorithm-by-coordinating-likes-and-comments-on-millions-of-posts","status":"publish","type":"post","link":"https:\/\/www.rbsitsoftwaresolution.in\/blog\/instagram-pods-game-the-algorithm-by-coordinating-likes-and-comments-on-millions-of-posts.html","title":{"rendered":"Instagram \u2018pods\u2019 game the algorithm by coordinating likes and comments on millions of posts"},"content":{"rendered":"

Researchers at NYU have identified hundreds of groups<\/a> of Instagram users, some with thousands of members, that systematically exchange likes and comments in order to game the service\u2019s algorithms and boost visibility. In the process, they also trained machine learning agents to identify whether a post has been juiced in this way.<\/p>\n

\u201cPods,\u201d as they\u2019ve been dubbed, straddle the line between real and fake engagement, making them tricky to detect or take action against. And while they used to be a niche threat (and still are compared with fake account and bot activity), the practice is growing in volume and efficacy.<\/p>\n

Pods are easily found via searching online, and some are open to the public. The most common venue for them is Telegram, as it\u2019s more or less secure and has no limit to the number of people who can be in a channel. Posts linked in the pod are liked and commented on by others in the group, with the effect of those posts being far more likely to be spread widely by Instagram\u2019s <\/a> recommendation algorithms, boosting organic engagement.<\/p>\n

Reciprocity as a service<\/h2>\n

The practice of groups mutually liking one another\u2019s posts is called reciprocity abuse, and social networks are well aware of it, having removed setups of this type before. But the practice has never been studied or characterized in detail, the team from NYU\u2019s Tandon School of Engineering explained.<\/p>\n

\u201cIn the past they\u2019ve probably been focused more on automated threats, like giving credentials to someone to use, or things done by bots,\u201d said lead author of the study Rachel Greenstadt. \u201cWe paid attention to this because it\u2019s a growing problem, and it\u2019s harder to take measures against.\u201d<\/p>\n

On a small scale it doesn\u2019t sound too threatening, but the study found nearly 2 million posts that had been manipulated by this method, with more than 100,000 users taking part in pods. And that\u2019s just the ones in English, found using publicly available data. The paper describing the research was published in the Proceedings of the World Wide Web Conference and can be read here<\/a>.<\/p>\n

Importantly, the reciprocal liking does more than inflate apparent engagement. Posts submitted to pods got large numbers of artificial likes and comments, yes, but that activity deceived Instagram\u2019s algorithm<\/a> into promoting them further, leading to much more engagement even on posts not<\/em> submitted to the pod.<\/p>\n

\n

Inside the Instagram AI that fills Explore with fresh, juicy content<\/a><\/p>\n<\/blockquote>\n

\n

When contacted for comment, Instagram initially said that this activity \u201cviolates our policies and we have numerous measures in place to stop it,\u201d and said that the researchers had not collaborated with the company on the research.<\/p>\n

In fact the team was in contact with Instagram\u2019s abuse team from early on in the project, and it seems clear from the study that whatever measures are in place have not, at least in this context, had the desired effect. I pointed this out to the representative and will update this post if I hear back with any more information.<\/p>\n

\u201cIt\u2019s a grey area\u201d<\/h2>\n

But don\u2019t reach for the pitchforks just yet \u2014 the fact is this kind of activity is remarkably hard to detect, because really it\u2019s identical in many ways to a group of friends or like-minded users engaging with each others\u2019 content in exactly the way Instagram would like. And really, even classifying the behavior as abuse isn\u2019t so simple.<\/p>\n

\u201cIt\u2019s a grey area, and I think people on Instagram think of it as a grey area,\u201d said Greenstadt. \u201cWhere does it end? If you write an article and post it on social media and send it to friends, and they like it, and they sometimes do that for you, are you part of a pod? The issue here is not necessarily that<\/em> people are doing this, but how<\/em> the algorithm should treat this action, in terms of amplifying or not amplifying that content.\u201d<\/p>\n

Obviously if people are doing it systematically with thousands of users and even charging for access (as some groups do), that amounts to abuse. But drawing the line isn\u2019t easy.<\/p>\n

More important is that the line can\u2019t be drawn unless you first define the behavior, which the researchers did by carefully inspecting the differences in patterns of likes and comments on pod-boosted and ordinary posts.<\/p>\n

\u201cThey have different linguistic signatures,\u201d explained co-author Janith Weerasinghe. \u201cWhat words they use, the timing patterns.\u201d<\/p>\n

As you might expect, strangers obligated to comment on posts they don\u2019t actually care about tend to use generic language, saying things like \u201cnice pic\u201d or \u201cwow\u201d rather than more personal remarks. Some groups actually warn against this, Weerasinghe said, but not many.<\/p>\n

The list of top words used reads, predictably, like the comment section on any popular post, though perhaps that speaks to a more general lack of expressiveness on Instagram than anything else:<\/p>\n

<\/a>But statistical analysis of thousands of such posts, both pod-powered and normal, showed a distinctly higher prevalence of \u201cgeneric support\u201d comments, often showing up in a predictable pattern.<\/p>\n

This data was used to train a machine learning model, which when set loose on posts it had never seen, was able to identify posts given the pod treatment with as high as 90% accuracy. This could help surface other pods \u2014 and make no mistake, this is only a small sample of what\u2019s out there.<\/p>\n

\u201cWe got a pretty good sample for the time period of the easily accessible, easily findable pods,\u201d said Greenstadt. \u201cThe big part of the ecosystem that we\u2019re missing is pods that are smaller but more lucrative, that have to have a certain presence on social media already to join. We\u2019re not influencers, so we couldn\u2019t really measure that.\u201d<\/p>\n

The numbers of pods and the posts they manipulate has grown steadily over the last two years. About 7,000 posts were found during March of 2017. A year later that number had jumped to nearly 55,000. March of 2019 saw over 100,000, and the number continued to increase through the end of the study\u2019s data. It\u2019s safe to say that pods are now posting over 4,000 times a day \u2014 and each one is getting a large amount of engagement, both artificial and organic. Pods now have 900 users on average<\/em>, and some had over 10,000.<\/p>\n

\n

Instagram says growth hackers are behind spate of fake Stories views<\/a><\/p>\n<\/blockquote>\n

\n

You may be thinking: \u201cIf a handful of academics using publicly available APIs and Google could figure this out, why hasn\u2019t Instagram?\u201d<\/p>\n

As mentioned before, it\u2019s possible the teams there have simply not considered this to be a major threat and consequently have not created policies or tools to prevent it. Rules proscribing using a \u201cthird party app or service to generate fake likes, follows, or comments\u201d arguably don\u2019t apply to these pods, since in many ways they\u2019re identical to perfectly legitimate networks of users (though Instagram clarified that it considers pods as violating the rule). And certainly the threat from fake accounts and bots is of a larger scale.<\/p>\n

And while it\u2019s possible that pods could be used as a venue for state-sponsored disinformation or other political purposes, the team didn\u2019t notice anything happening along those lines (though they were not looking for it specifically). So for now the stakes are still relatively small.<\/p>\n

That said, Instagram clearly has access to data that would help to define and detect this kind of behavior, and its policies and algorithms could be changed to accommodate it. No doubt the NYU researchers would love to help.<\/p>\n

Article source: http:\/\/feedproxy.google.com\/~r\/techcrunch\/social\/~3\/XoF2RR6iUEE\/<\/p>","protected":false},"excerpt":{"rendered":"

Researchers at NYU have identified hundreds of groups of Instagram users, some with thousands of members, that systematically exchange likes and comments in order to game the service\u2019s algorithms and <\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[3],"tags":[10,7,14,15,6,12,11],"class_list":["post-18370","post","type-post","status-publish","format-standard","hentry","category-latest-update","tag-computer-news","tag-downloads","tag-microsoft-download-news","tag-networking-updates","tag-technology-update","tag-wordpress-plugin-download","tag-wordpress-theme-download"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t