MSM-BD: Multimodal Social Media Bot Detection Using Heterogeneous Information

TL;DR

This paper introduces MSM-BD, a novel multimodal approach leveraging heterogeneous social media data and a cross-modal attention mechanism to improve the accuracy of detecting social media bots.

Contribution

We propose MSM-BD, a new multimodal detection framework that uses heterogeneous information and a novel cross-modal residual cross-attention mechanism for social bot detection.

Findings

MSM-BD outperforms existing methods on TwiBot-22 dataset.

The cross-modal residual cross-attention improves detection accuracy.

Multimodal features significantly enhance bot detection performance.

Abstract

Although social bots can be engineered for constructive applications, their potential for misuse in manipulative schemes and malware distribution cannot be overlooked. This dichotomy underscores the critical need to detect social bots on social media platforms. Advances in artificial intelligence have improved the abilities of social bots, allowing them to generate content that is almost indistinguishable from human-created content. These advancements require the development of more advanced detection techniques to accurately identify these automated entities. Given the heterogeneous information landscape on social media, spanning images, texts, and user statistical features, we propose MSM-BD, a Multimodal Social Media Bot Detection approach using heterogeneous information. MSM-BD incorporates specialized encoders for heterogeneous information and introduces a cross-modal fusion technology, Cross-Modal Residual Cross-Attention (CMRCA), to enhance detection accuracy. We validate the effectiveness of our model through extensive experiments using the TwiBot-22 dataset.