"Four automatic rumor detection models based on artificial intelligencenatural language processing.
Rumor Detection on Twitter Using Multiloss Hierarchical BiLSTM with an Attenuation Factor
Exploiting Microblog Conversation Structures to Detect Rumors
Birds of a Feather Rumor Together? Exploring HomogeneityConversation Structure in Social Media for Rumor Detection
Meet The Truth: Leverage Objective FactsSubjective Views for Interpretable Rumor Detection
Experimental results show that these four models have greatly improved the accuracy of rumor detection, surpassing other SOTA models."

Our models break the limitation of the traditional sentence embedding,innovatively integrates the idea of multi-task, which ensures the detection accuracy of the modelreduces the training time. We are the first one to simulate a suspicious claimits replies as a topological structure object,we are also the first one to propose a homogeneous rumor detection model. We are the first to propose an evidence-providing automated rumour detection model.

Our automatic rumor detection models can directly work on the social media platform (TwitterWeibo, WeChat, Facebook, etc.)fact check centers, as the form of interface,carry out real-time rumor detection on the constantly updated text data stream in the social media. It can restrain the spread of rumors in time,has great practicalpractical significance.

天使投資人、策略合作夥伴