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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

As malicious actors employ increasingly advanced and widespread bots todisseminate misinformation and manipulate public opinion, the detection ofTwitter bots has become a crucial task. Though graph-based Twitter botdetection methods achieve state-of-the-art performance, we find that theirinference depends on the neighbor users multi-hop away from the targets, andfetching neighbors is time-consuming and may introduce bias. At the same time,we find that after finetuning on Twitter bot detection, pretrained languagemodels achieve competitive performance and do not require a graph structureduring deployment. Inspired by this finding, we propose a novel bot detectionframework LMBot that distills the knowledge of graph neural networks (GNNs)into language models (LMs) for graph-less deployment in Twitter bot detectionto combat the challenge of data dependency. Moreover, LMBot is compatible withgraph-based and graph-less datasets. Specifically, we first represent each useras a textual sequence and feed them into the LM for domain adaptation. Forgraph-based datasets, the output of LMs provides input features for the GNN,enabling it to optimize for bot detection and distill knowledge back to the LMin an iterative, mutually enhancing process. Armed with the LM, we can performgraph-less inference, which resolves the graph data dependency and samplingbias issues. For datasets without graph structure, we simply replace the GNNwith an MLP, which has also shown strong performance. Our experimentsdemonstrate that LMBot achieves state-of-the-art performance on four Twitterbot detection benchmarks. Extensive studies also show that LMBot is morerobust, versatile, and efficient compared to graph-based Twitter bot detectionmethods.

LMBot: Distilling Graph Knowledge into Language Model for Graph-less Deployment in Twitter Bot Detection