Multimodal Detection of Bots on X (Twitter) using Transformers
Loukas Ilias, Ioannis Michail Kazelidis, Dimitris Askounis

TL;DR
This paper introduces a novel multimodal transformer-based approach for bot detection on Twitter, utilizing user descriptions and images, and demonstrates superior performance over existing methods on benchmark datasets.
Contribution
It is the first to employ only user descriptions and images with transformer-based models and multimodal fusion techniques for bot detection.
Findings
Outperforms state-of-the-art methods on Cresci'17 and TwiBot-20 datasets.
Shows effectiveness of multimodal fusion techniques like crossmodal attention.
Demonstrates that transformer-based models improve bot detection accuracy.
Abstract
Although not all bots are malicious, the vast majority of them are responsible for spreading misinformation and manipulating the public opinion about several issues, i.e., elections and many more. Therefore, the early detection of bots is crucial. Although there have been proposed methods for detecting bots in social media, there are still substantial limitations. For instance, existing research initiatives still extract a large number of features and train traditional machine learning algorithms or use GloVe embeddings and train LSTMs. However, feature extraction is a tedious procedure demanding domain expertise. Also, language models based on transformers have been proved to be better than LSTMs. Other approaches create large graphs and train graph neural networks requiring in this way many hours for training and access to computational resources. To tackle these limitations, this is…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMisinformation and Its Impacts · Topic Modeling · Spam and Phishing Detection
Methods*Communicated@Fast*How Do I Communicate to Expedia? · Depthwise Convolution · Sigmoid Activation · Pointwise Convolution · Depthwise Separable Convolution · Dense Connections · Squeeze-and-Excitation Block · Batch Normalization · Convolution · Dropout
