SeGA: Preference-Aware Self-Contrastive Learning with Prompts for Anomalous User Detection on Twitter
This addresses the problem of detecting malicious users (e.g., for misinformation or cyberbullying) on social media, offering a novel approach beyond bot detection, though it is domain-specific to Twitter.
The paper tackles anomalous user detection on Twitter by proposing SeGA, a preference-aware self-contrastive learning method that leverages user preferences and prompts, achieving state-of-the-art performance with improvements of +3.5% to 27.6% on the TwBNT benchmark.
In the dynamic and rapidly evolving world of social media, detecting anomalous users has become a crucial task to address malicious activities such as misinformation and cyberbullying. As the increasing number of anomalous users improves the ability to mimic normal users and evade detection, existing methods only focusing on bot detection are ineffective in terms of capturing subtle distinctions between users. To address these challenges, we proposed SeGA, preference-aware self-contrastive learning for anomalous user detection, which leverages heterogeneous entities and their relations in the Twittersphere to detect anomalous users with different malicious strategies. SeGA utilizes the knowledge of large language models to summarize user preferences via posts. In addition, integrating user preferences with prompts as pseudo-labels for preference-aware self-contrastive learning enables the model to learn multifaceted aspects for describing the behaviors of users. Extensive experiments on the proposed TwBNT benchmark demonstrate that SeGA significantly outperforms the state-of-the-art methods (+3.5\% ~ 27.6\%) and empirically validate the effectiveness of the model design and pre-training strategies. Our code and data are publicly available at https://github.com/ying0409/SeGA.