The Pod People: Understanding Manipulation of Social Media Popularity via Reciprocity Abuse
Open accessAbstract
Online Social Network (OSN) Users’ demand to increase their account popularity has driven the creation of an underground ecosystem that provides services or techniques to help users manipulate content curation algorithms. One method of subversion that has recently emerged occurs when users form groups, called pods, to facilitate reciprocity abuse, where each member reciprocally interacts with content posted by other members of the group. We collect 1.8 million Instagram posts that were posted in pods hosted on Telegram. We first summarize the properties of these pods and how they are used, uncovering that they are easily discoverable by Google search and have a low barrier to entry. We then create two machine learning models for detecting Instagram posts that have gained interaction through two different kinds of pods, achieving 0.91 and 0.94 AUC, respectively. Finally, we find that pods are effective tools for increasing users’ Instagram popularity, we estimate that pod utilization leads to a significantly increased level of likely organic comment interaction on users’ subsequent posts.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
(2003) · Journal of Machine Learning Research · doi:10.5555/944919.944937 · Cited by 32,337 · see citing works
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707 · cited 1× · see citing works
“We measured the łimportancež of each feature with Shapley Additive Explanations, or SHAP values [17, 18], which captures the contribution of each feature based on local explanations [22] and principles of game”
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555 · see citing works
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2002) · The MIT Press eBooks · doi:10.7551/mitpress/1120.003.0082 · Cited by 12,649 · see citing works
Gauriat, C.-M., Pencolé, Y., Ribot, P., et al. (2024) · HAL · doi:10.4230/oasics.dx.2024.27 · Cited by 12,623 · see citing works
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278 · see citing works
ALGORITHMS FOR NON-NEGATIVE MATRIX FACTORIZATION
Seung, D., & Lee, L.-W. (2001) · Cited by 4,753 · see citing works
Consistent Individualized Feature Attribution for Tree Ensembles
Lundberg, S. M., Erion, G. G., & Lee, S.-I. (2018) · arXiv · doi:10.48550/arxiv.1802.03888 · Cited by 1,430 · see citing works
Exploring Topic Coherence over Many Models and Many Topics
Stevens, K., Kegelmeyer, P., Andrzejewski, D., & Buttler, D. J. (2012) · Cited by 473 · see citing works
CopyCatch: stopping group attacks by spotting lockstep behavior in social networks
Beutel, A., Xu, W., Guruswami, V., Palow, C., & Faloutsos, C. (2013) · Proceedings of the 22nd international conference on World Wide Web · doi:10.1145/2488388.2488400 · Cited by 335 · cited 1× · see citing works
“Recent advances in scalably detecting this lockstep behaviour (orchestrated actions by sets of users which have a very low likelihood of happening spontaneously or organically) [3] have allowed OSN platforms such as YouTube to successfully address this problem [16].”
Uncovering Large Groups of Active Malicious Accounts in Online Social Networks
Cao, Q., Yang, X., Yu, J., & Palow, C. (2014) · Proceedings of the 2014 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2660267.2660269 · Cited by 274 · see citing works
Towards Detecting Anomalous User Behavior in Online Social Networks
Viswanath, B., Gummadi, K. P., Bashir, M. A., Krishnamurthy, B., Crovella, M. E., Guha, S., & Mislove, A. E. (2014) · Cited by 236 · see citing works
Sanderson, M. (2010) · Natural Language Engineering · doi:10.1017/s1351324909005129 · Cited by 210 · see citing works
Stringhini, G., Wang, G., Egele, M., Kruegel, C., Vigna, G., Zheng, H., & Zhao, B. Y. (2013) · Proceedings of the 2013 conference on Internet measurement conference · doi:10.1145/2504730.2504731 · Cited by 169 · cited 1× · see citing works
“Stringhini et al. [25] investigates Twitter follower markets which sell Twitter follows using automated methods.”
Mathur, A., Narayanan, A., & Chetty, M. (2018) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3274388 · Cited by 86 · cited 1× · see citing works
“The harms of these manipulation attacks range from increasing the reach of influencers’ deceptively promoted content [20] to the amplification of extreme political rhetoric by nation states to influence elections [8, 21].”
De Cristofaro, E., Friedman, A., Jourjon, G., Kaafar, M. A., & Shafiq, M. Z. (2014) · Proceedings of the 2014 Conference on Internet Measurement Conference · doi:10.1145/2663716.2663729 · Cited by 85 · cited 2× · see citing works
“De Cristofaro et al. [9] explored the landscape of łlike farmsž, a related curation algorithm manipulation technique.”
Robust detection of comment spam using entropy rate
Kantchelian, A., Ma, J. H., Huang, L., et al. (2012) · doi:10.1145/2381896.2381907 · Cited by 58 · cited 1× · see citing works
“used to detect spam comments on social media.[2].”
Li, Y., Martinez, O., Chen, X., Li, Y., & Hopcroft, J. E. (2016) · International World Wide Web Conference (WWW) · doi:10.1145/2872427.2882972 · Cited by 53 · cited 1× · see citing works
“Recent advances in scalably detecting this lockstep behaviour (orchestrated actions by sets of users which have a very low likelihood of happening spontaneously or organically) [3] have allowed OSN platforms such as YouTube to successfully address this problem [16].”
No Reciprocity in "Liking" Photos
Jang, J. Y., Han, K., & Lee, D. (2015) · ACM Conference on Hypertext and Social Media (HT) · doi:10.1145/2700171.2791043 · Cited by 41 · cited 1× · see citing works
“This is similar to the approach taken by Jang et al. [12], in which they computed the entropy of LDA topic probabilities to measure the diversity of a user’s posts.”
In a World That Counts: Clustering and Detecting Fake Social Engagement at ScalePreprint
Li, Y., Martinez, O., Chen, X., Li, Y., & Hopcroft, J. E. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.05457 · Cited by 39 · cited 1× · see citing works
“Recent advances in scalably detecting this lockstep behaviour (orchestrated actions by sets of users which have a very low likelihood of happening spontaneously or organically) [3] have allowed OSN platforms such as YouTube to successfully address this problem [16].”
Measuring and mitigating oauth access token abuse by collusion networks
Farooqi, S., Zaffar, F., Leontiadis, N., & Shafiq, Z. (2017) · ACM Internet Measurement Conference (IMC) · doi:10.1145/3131365.3131404 · Cited by 20 · cited 1× · see citing works
“A 2017 study by Farooqi et al. [11] first described this thriving ecosystem of large-scale reputation manipulation services on Facebook that leverage the principle of collusion.”
DeKoven, L. F., Pottinger, T., Savage, S., Voelker, G. M., & Leontiadis, N. (2018) · ACM Internet Measurement Conference (IMC) · doi:10.1145/3278532.3278537 · Cited by 4 · cited 3× · see citing works
“DeKoven et al. [10] characterizes similar collusion networks on Instagram.”
Influential
Flagged first, then by citations
Research works printed but not linked: 3
- 2019, News Feed FYI. https://newsroom.fb.com/news/category/news-feed-fyi/. [Online
- Stout Dustin, 2019, Social Media Statistics 2019: Top Networks By the Numbers. https://dustinstout.com/social-media-statistics/. [Online
- Tooby Alex, 2019, The Truth About Instagram Pods – Do They Really Work To Increase Your Engagement?https://alextooby.com/instagram-pods/. [Online
Cited by
Sorted by citations
Understanding the Effect of Deplatforming on Social Networks
Ali, S., Saeed, M. H., Aldreabi, E., Blackburn, J., De Cristofaro, E., Zannettou, S., & Stringhini, G. (2021) · 13th ACM Web Science Conference 2021 · doi:10.1145/3447535.3462637 · Cited by 109 · see citing works
“A wealth of research has studied malicious accounts on social networks, from those involved in sending spam [22, 54, 57] to performing fraud [15, 26, 63], to taking part in online harassment [12, 19] Alorainy et al.”
BackgroundLing, C., Stringhini, G., Balci, U., & Blackburn, J. (2021) · IEEE Security & Privacy · doi:10.1109/msec.2021.3127392 · Cited by 57 · see citing works
On the Dynamics of Political Discussions on Instagram: A Network Perspective
Ferreira, C. H. G., Murai, F., Silva, A. P. C., Almeida, J. M., Trevisan, M., Vassio, L., Mellia, M., & Drago, I. (2021) · Online Soc. Networks Media · doi:10.1016/j.osnem.2021.100155 · Cited by 49 · see citing works
Miguel, C., Clare, C., Ashworth, C. J., & Hoang, D. (2022) · Journal of Marketing Management · doi:10.1080/0267257x.2022.2041705 · Cited by 27 · see citing works
“Engagement pods (EP) are online communities designed to facilitate systematic engagement where ‘users interact with each other‘s content, thereby increasing its popularity and consequent importance to the content curation algorithm’ (Weerasinghe et al., 2020, p. 1874).”
BackgroundResultUnderstanding Incentivized Mobile App Installs on Google Play Store
Farooqi, S., Feal, Á., Lauinger, T., McCoy, D., Shafiq, Z., & Vallina-Rodriguez, N. (2020) · Proceedings of the ACM Internet Measurement Conference · doi:10.1145/3419394.3423662 · Cited by 22 · see citing works
“and Instagram [25–27, 32, 57, 58, 61, 63].”
Self-citationFrom Symbols to Embeddings: A Tale of Two Representations in Computational Social Science
Chen, H., Yang, C. H., Zhang, X., Liu, Z., Sun, M., & Jin, J. (2021) · Journal of Social Computing · doi:10.23919/jsc.2021.0011 · Cited by 16 · see citing works
It’s a Trap! Detection and Analysis of Fake Channels on Telegram
Morgia, M. L., Mei, A., Mongardini, A. M., & Wu, J. (2023) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws60048.2023.00026 · Cited by 16 · see citing works
Uncovering the Dark Side of Telegram: Fakes, Clones, Scams, and Conspiracy MovementsPreprint
Morgia, M. L., Mei, A., Mongardini, A. M., & Wu, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.13530 · Cited by 33 · see citing works
“[39] reveal that Telegram hosts several organized groups, called pods, where each member interacts with each other’s content to increase the popularity of their Instagram accounts.”
BackgroundTGDataset: Collecting and Exploring the Largest Telegram Channels Dataset
Morgia, M. L., Mei, A., & Mongardini, A. M. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3690624.3709397 · Cited by 9 · see citing works
“This is the motivation behind the creation of the TGDataset.”
Topic-wise Exploration of the Telegram Group-verse
Perlo, A., Paoletti, G., Jha, N., et al. (2025) · doi:10.1145/3701716.3717506 · Cited by 8 · see citing works
“The use of Telegram to perform illicit activities (e.g., pump-and-dump activities in cryptocurrency markets [41], manipulation of social media popularity [39]) has also been previously addressed.”
Pretending to be a VIP! Characterization and Detection of Fake and Clone Channels on Telegram
Morgia, M. L., Mei, A., Mongardini, A. M., & Wu, J. (2024) · ACM Transactions on the Web · doi:10.1145/3705014 · Cited by 9 · see citing works
“In their work, Weerasinghe et al. [56] reveal that Telegram hosts several organized groups, called pods, where each member interacts with each other’s content to increase the popularity of their Instagram accounts.”
DECIFE: Detecting Collusive Users Involved in Blackmarket Following Services on Twitter
Dutta, H. S., Aggarwal, K., & Chakraborty, T. (2021) · ACM Conference on Hypertext and Social Media (HT) · doi:10.1145/3465336.3475108 · Cited by 6 · see citing works
“[37] studied models for detecting Instagram posts that gained interaction through collusive networks.”
Background#TeamFollowBack: Detection & Analysis of Follow Back Accounts on Social Media
Elmas, T., Randl, M., & Attia, Y. (2024) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v18i1.31321 · Cited by 3 · see citing works
Influencer CartelsPreprint
Hinnosaar, M., & Hinnosaar, T. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3786617 · Cited by 4 · see citing works
Ling, C., & Stringhini, G. (2024) · European Symposium on Usable Security (EuroUSEC) · doi:10.1145/3688459.3688466 · Cited by 2 · see citing works
“Online abuse carried out on social networks has been a common topic of study by the security community, spanning from fake accounts carrying out spam campaigns [4, 9, 16, 19, 40, 47, 49], astroturfing campaigns [10, 41, 46], and online disinformation operations [3, 28, 32, 38, 39, 50].”
DECIFE: Detecting Collusive Users Involved in Blackmarket Following Services on Twitter
Dutta, H. S., Aggarwal, K., & Chakraborty, T. (2024) · Figshare · Cited by 2 · see citing works
Towards understanding bogus traffic service in online social networks
He, P., Zhang, X., Lin, C., Wang, T., & Ji, S. (2024) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2300068 · Cited by 1 · see citing works
“I Am My Own Bot”: Everyday Resistance in Online Fashion Resale
Espinosa, S. M., & DiSalvo, C. F. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791594 · Cited by 1 · see citing works
“Pods are small communities of users which ‘artificially’ inflate engagement metrics through reciprocal interactions among users which results in both ‘artificial’ and ‘organic’ traffic metric inflation [98].”
Saeed, M. H., Ali, S., Paudel, P., Blackburn, J., & Stringhini, G. (2024) · International Symposium on Research in Attacks, Intrusions and Defenses (RAID) · doi:10.1145/3678890.3678911 · Cited by 3 · see citing works
“Previous research extensively studied follower markets [50], [53], [65] and the detection of accounts involved in such activity [69].”
From Symbols to Embeddings: A Tale of Two Representations in Computational Social SciencePreprint
Chen, H., Yang, C. H., Zhang, X., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.14198 · Cited by 1 · see citing works
Karagiorgakis, A., & Aaron, K. (2024) · The American Journal of Psychology · doi:10.5406/19398298.137.1.03
- Authors
- Weerasinghe, J., Flanigan, B., Stein, A., McCoy, D., & Greenstadt, R.
- Affiliations
- New York University (US)
- Drexel University (US)
- Venue
- Proceedings of The Web Conference 2020
- Publisher
- ACM
- Published
- 2020-04-20
- Pages
- 1874-1884
- OpenAlex
- W3012738370
- Semantic Scholar
- 02ebd98c7e5e6fe53f64363c7bb7fa6ef15b47c0
- Cited by
- 21
- References
- 22
- Citations by year
- 2026: 1 · 2025: 2 · 2024: 7 · 2023: 1 · 2022: 1 · 2021: 8 · 2020: 1
- FWCI
- 2.16
- Type
- conference paper
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Topics
- Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
- Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Keywords
- pods, Instagram, telegrams, social networking sites
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
