Co-commenters as clues

A partial-label approach to detecting anomalous channels on Youtube

Bibliographic Data

ID16859403
AuthorsRidwan Amure (University of Arkansas at Little Rock), Neil Agarwal (0000-0002-5612-4753, University of Arkansas at Little Rock, corresponding author)
Year2025
Volume15
Issue1
Publication date2025-07-30
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueSocial Network Analysis and Mining (JOURNAL)
Journal identifiersISSN: 1869-5450 • E-ISSN: 1869-5469
PublisherSpringer Science and Business Media LLC (PUBLISHER)
DOI10.1007/s13278-025-01493-0
OpenAlexW4412753896
LanguageEN
References cited26

We propose a semi-supervised approach that finds anomalous YouTube channels by combining co-commenter networks and engagement features. Our method, named SEPS (Semi-Supervised Embedding-based Propagation Scoring), uses a small set of labeled anomalies to guide the learning process. It trains a graph neural network to embed nodes, spreads those partial labels through a simple classification head, and flags channels that appear suspicious. The model was tested on real data from the Indo-Pacific region which spans 97 channels, 702,160 videos, 12.5 million commenters, and 123.9 million comments. Further tests on synthetic data show that SEPS outperforms older methods in recall, precision, and F1-score. It detects more unlabeled anomalies with fewer false alarms. We also show that it remains effective when only a handful of known anomalies are present, and it can maintain high cluster purity under these conditions. In addition, we discuss how the model can scale to larger datasets and adapt to changes in user behavior. This work contributes a robust way to spot suspicious channels in real-world environments where full labels are scarce

Social media · World Wide Web · Complex Network Analysis Techniques · Computer Science · Misinformation and Its Impacts · Sentiment Analysis and Opinion Mining

Tools

Open DOIOpen Access