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

Information diffusion prediction aims at predicting the target users in theinformation diffusion path on social networks. Prior works mainly focus on theobserved structure or sequence of cascades, trying to predict to whom thiscascade will be infected passively. In this study, we argue that user intentunderstanding is also a key part of information diffusion prediction. Wethereby propose a novel Multi-scale Context-enhanced Dynamic Attention Network(MCDAN) to predict which user will most likely join the observed currentcascades. Specifically, to consider the global interactive relationship amongusers, we take full advantage of user friendships and global cascadingrelationships, which are extracted from the social network and historicalcascades, respectively. To refine the model's ability to understand the user'spreference for the current cascade, we propose a multi-scale sequentialhypergraph attention module to capture the dynamic preference of users atdifferent time scales. Moreover, we design a contextual attention enhancementmodule to strengthen the interaction of user representations within the currentcascade. Finally, to engage the user's own susceptibility, we construct asusceptibility label for each user based on user susceptibility analysis anduse the rank of this label for auxiliary prediction. We conduct experimentsover four widely used datasets and show that MCDAN significantly overperformsthe state-of-the-art models. The average improvements are up to 10.61% in termsof Hits@100 and 9.71% in terms of MAP@100, respectively.

MCDAN: a Multi-scale Context-enhanced Dynamic Attention Network for Diffusion Prediction