aiqbench analysis
This research investigates whether combining textual, visual, and metadata signals significantly improves fake account detection compared to strong baseline features. The study concludes that under practical constraints, high-quality metadata alone is highly predictive, while complex multimodal fusion offers only marginal gains and graph-based models underperform in subsampled conditions. For practitioners building bot detection systems, this suggests prioritizing feature engineering and data richness over architectural complexity.
Improving Fake Profile Detection Through Multimodal Learning and Research-Guided Feature Integration
arXiv:2610.23926v1 Announce Type: new Abstract: Fake accounts continue to undermine online platforms, yet it remains unclear whether multimodal learning offers meaningful improvements over strong metadata baselines or graph-based approaches. In this work, we study bot detection by integrating textual, visual, and account metadata signals on the TwiBot-22 benchmark using a subsample of 30,000 users. We propose a multimodal framework combining pretrained textual (XLM-RoBERTa) and visual (CLIP) embeddings with structured account-level features such as follower counts, posting frequency, and account age, and evaluate multiple modality combinations using CatBoost alongside a Relational Graph Convolutional Network (R-GCN). Results show that metadata alone is highly predictive, while multimodal fusion yields only marginal and largely statistically insignificant gains. The graph-based model underperforms classical variants under the subsampled graph conditions of this study. Overall, our findings suggest that under practical constraints, feature quality and metadata richness matter more than fusion complexity.
Abstract:Fake accounts continue to undermine online platforms, yet it remains unclear whether multimodal learning offers meaningful improvements over strong metadata baselines or graph-based approaches. In this work, we study bot detection by integrating textual, visual, and account metadata signals on the TwiBot-22 benchmark using a subsample of 30,000 users. We propose a multimodal framework combining pretrained textual (XLM-RoBERTa) and visual (CLIP) embeddings with structured account-level features such as follower counts, posting frequency, and account age, and evaluate multiple modality combinations using CatBoost alongside a Relational Graph Convolutional Network (R-GCN). Results show that metadata alone is highly predictive, while multimodal fusion yields only marginal and largely statistically insignificant gains. The graph-based model underperforms classical variants under the subsampled graph conditions of this study. Overall, our findings suggest that under practical constraints, feature quality and metadata richness matter more than fusion complexity.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2610.23926 [cs.LG]
(or arXiv:2610.23926v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.23926 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 237 words