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

Persuasion modeling is a key building block for conversational agents.Existing works in this direction are limited to analyzing textual dialoguecorpus. We argue that visual signals also play an important role inunderstanding human persuasive behaviors. In this paper, we introduce the firstmultimodal dataset for modeling persuasion behaviors. Our dataset includes 199dialogue transcriptions and videos captured in a multi-player social deductiongame setting, 26,647 utterance level annotations of persuasion strategy, andgame level annotations of deduction game outcomes. We provide extensiveexperiments to show how dialogue context and visual signals benefit persuasionstrategy prediction. We also explore the generalization ability of languagemodels for persuasion modeling and the role of persuasion strategies inpredicting social deduction game outcomes. Our dataset, code, and models can befound at https://persuasion-deductiongame.socialai-data.org.

Werewolf Among Us: A Multimodal Dataset for Modeling Persuasion Behaviors in Social Deduction Games