A State-independent and Time-evolving Network for Early Rumor Detection in Social Media

Abstract

In this paper, we study automatic rumor detection for in social media at the event level where an event consists of a sequence of posts organized according to the posting time. It is common that the state of an event is dynamically evolving. However, most of the existing methods to this task ignored this problem, and established a global representation based on all the posts in the event's life cycle. Such coarse-grained methods failed to capture the event's unique features in different states. To address this limitation, we propose a state-independent and time-evolving Network (STN) for rumor detection based on fine-grained event state detection and segmentation. Given an event composed of a sequence of posts, STN first predicts the corresponding sequence of states and segments the event into several state-independent sub-events. For each sub-event, STN independently trains an encoder to learn the feature representation for that sub-event and incrementally fuses the representation of the current sub-event with previous ones for rumor prediction. This framework can more accurately learn the representation of an event in the initial stage and enable early rumor detection. Experiments on two benchmark datasets show that STN can significantly improve the rumor detection accuracy in comparison with some strong baseline systems. We also design a new evaluation metric to measure the performance of early rumor detection, under which STN shows a higher advantage in comparison.

DDGCN: Dual Dynamic Graph Convolutional Networks for Rumor Detection on Social Media

“…Liu et al (Liu and Wu 2018) models the temporal structure by combining the recurrent and convolutional networks. Xia et al (Xia, Xuan, and Yu 2020) proposes a state-independent and time-evolving network for rumor detection based on fine-grained event state detection and segmentation. Huang et al (Huang et al 2020) proposes a spatial-temporal structure neural network for rumor detection.…”

“…The temporal structure refers to the sequence and interval of the (replied or forwarded) messages along the timeline, which can be used to further differentiate the diffusion patterns (Huang et al 2020;Xia, Xuan, and Yu 2020). For example, considering two comments r a and r b which corresponds to the same post.…”

Rumor Detection with Self-supervised Learning on Texts and Social Graph

“…Farinneya et al [71] design an Active Transfer Learning (ATL) strategy to identify rumors with a limited amount of annotated data. Xia et al [72] propose a state-independent and time-evolving Network which captures the event's unique features in different states. At the early stage, there is limited propagation information to utilize.…”

Open challenges for Machine Learning based Early Decision-Making research

“…Another application example is the moderation of social networking platforms, with early deletion of inappropriate contents and automatic closure of fraudulent accounts (see Section 9.4). In the Machine-Learning literature, there is little work which considers timeevolving texts [42,43] even though this is likely a future application area of considerable interest, and the development of ML-EDM methods would enable to optimize the time of decision making for text data.…”