English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In the dynamic and rapidly evolving world of social media, detectinganomalous users has become a crucial task to address malicious activities suchas misinformation and cyberbullying. As the increasing number of anomaloususers improves the ability to mimic normal users and evade detection, existingmethods only focusing on bot detection are ineffective in terms of capturingsubtle distinctions between users. To address these challenges, we proposedSeGA, preference-aware self-contrastive learning for anomalous user detection,which leverages heterogeneous entities and their relations in the Twittersphereto detect anomalous users with different malicious strategies. SeGA utilizesthe knowledge of large language models to summarize user preferences via posts.In addition, integrating user preferences with prompts as pseudo-labels forpreference-aware self-contrastive learning enables the model to learnmultifaceted aspects for describing the behaviors of users. Extensiveexperiments on the proposed TwBNT benchmark demonstrate that SeGA significantlyoutperforms the state-of-the-art methods (+3.5\% ~ 27.6\%) and empiricallyvalidate the effectiveness of the model design and pre-training strategies. Ourcode and data are publicly available at https://github.com/ying0409/SeGA.

SeGA: Preference-Aware Self-Contrastive Learning with Prompts for Anomalous User Detection on Twitter