Modeling Conversation Structure and Temporal Dynamics for Jointly Predicting Rumor Stance and Veracity

Wei, Penghui; Xu, Nan; Mao, Wenji

doi:10.18653/v1/d19-1485

Cited by 55 publications

(25 citation statements)

References 45 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid feature engineering, subsequent studies proposed data-driven methods based on neural networks such as RNN [32] and CNN [49] to automatically capture rumor-indicative patterns. Considering the close correlations among rumor and stance categories, multi-task learning framework was utilized to mutually reinforce rumor verification and stance detection tasks [20,21,34,46]. To model complex structures of post propagation, more advanced approaches were proposed to use tree kneral-based method [33,47], tree-structured RvNN [35,46], hybrid RNN-CNN model [27], variants of Transformer [16,31], graph coattention networks [28] and Bi-directional Graph Neural Networks (BiGCN) [4,23] for classify different kinds of rumors.…”

Section: Related Workmentioning

confidence: 99%

“…To alleviate feature engineering, Zhang et al [51] proposed to learn a hierarchical representation of stance classes to overcome the class imbalance problem. Further, multi-task learning framework was utilized to mutually reinforce stance detection and rumor classification simultaneously [20,21,34,46]. However, they generally require a large stance corpus annotated at post level for model training, which is a daunting issue.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, the voices of opposition and doubt seem to always appear among the posts along with the spread of rumors [36]; also, there are many skepticism and enquiries posts sparked to find out the claim's veracity [57]. Moreover, propagation structure provides valuable clues regarding how a claim is transmitted and opinionated by users over time [31,46]. Figure 1 exemplifies the dissemination of four types of rumorous claims, where each claim is represented as a propagation tree consisting of the source post and user responses.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Weakly Supervised Propagation Model for Rumor Verification and Stance Detection with Multiple Instance Learning

Yang¹,

Ma²,

Lin³

et al. 2022

Preprint

View full text Add to dashboard Cite

The diffusion of rumors on social media generally follows a propagation tree structure, which provides valuable clues on how an original message is transmitted and responded by users over time. Recent studies reveal that rumor verification and stance detection are two relevant tasks that can jointly enhance each other despite their differences. For example, rumors can be debunked by crosschecking the stances conveyed by their relevant posts, and stances are also conditioned on the nature of the rumor. However, stance detection typically requires a large training set of labeled stances at post level, which are rare and costly to annotate.Enlightened by Multiple Instance Learning (MIL) scheme, we propose a novel weakly supervised joint learning framework for rumor verification and stance detection which only requires bag-level class labels concerning the rumor's veracity. Specifically, based on the propagation trees of source posts, we convert the two multi-class problems into multiple MIL-based binary classification problems where each binary model is focused on differentiating a target class (of rumor or stance) from the remaining classes. Then, we propose a hierarchical attention mechanism to aggregate the binary predictions, including (1) a bottom-up/top-down tree attention layer to aggregate binary stances into binary veracity; and (2) a discriminative attention layer to aggregate the binary class into finer-grained classes. Extensive experiments conducted on three Twitter-based datasets demonstrate promising performance of our model on both claim-level rumor detection and post-level stance classification compared with state-of-the-art methods. CCS CONCEPTS• Computing methodologies → Natural language processing.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Weakly Supervised Propagation Model for Rumor Verification and Stance Detection with Multiple Instance Learning

Yang¹,

Ma²,

Lin³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Some scholars combine the rumor position classification task with the rumor veracity classification task by using the idea of multi-task learning [25], [33]. Recently, sequential stance classification attracts more and more interest.…”

Section: B Stance Classification Based On Sequencementioning

confidence: 99%

A Stochastic Attention CNN Model for Rumor Stance Classification

2020

View full text Add to dashboard Cite

Rumor stance classification is a task for identifying different stances about specific social media posts, and it is considered as an important step to prevent rumors from spreading. However, most previous studies for the rumor stance classification, which focus on content features of posts, ignore the textual information granularity and reading (or writing) habits of the public. In social networks, people may have different stances towards unverified posts with different reading habits. Based on this observation, we propose a Stochastic Attention Convolutional Neural Net (SACNN) under different textual information granularity to catch different habits of the public for the rumor stance classification task. Specifically, being treated as view-windows of readers, convolutional kernels in a SACNN contain trainable convolutional kernels and stochastic untrainable convolutional kernels, and different sizes of the stochastic convolutional kernels are used to simulate casual online reading habits and to extract course-grained features such as phrase features. After the convolutional layer, fine-grained features such as keywords can be extracted by a pooling layer. The experiments show that the average accuracy and F1 score of our proposed model are respectively 0.26% and 0.46% higher than the state-of-the-art results on the rumor stance classification task on PHEME dataset.

show abstract

“…The content of social media posts is text shorter than 140 words with rich auxiliary features, e.g., comments and user profiles. Among these features, comments are semantically relevant to a source post and support or deny the original claim (Wei et al, 2019;Bian et al, 2020). However, social media posts often have comments whose total length exceeds the input-length limitation of LMs, demanding pre-processing like truncation.…”

Section: Introductionmentioning

confidence: 99%

STANKER: Stacking Network based on Level-grained Attention-masked BERT for Rumor Detection on Social Media

Rao¹,

Miao²,

Jiang³

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Rumor detection on social media puts pretrained language models (LMs), such as BERT, and auxiliary features, such as comments, into use. However, on the one hand, rumor detection datasets in Chinese companies with comments are rare; on the other hand, intensive interaction of attention on Transformer-based models like BERT may hinder performance improvement. To alleviate these problems, we build a new Chinese microblog dataset named Weibo20 1 by collecting posts and associated comments from Sina Weibo and propose a new ensemble named STANKER (Stacking neTwork bAsed-on atteNtion-masKed BERT). STANKER adopts two level-grained attentionmasked BERT (LGAM-BERT) models as base encoders. Unlike the original BERT, our new LGAM-BERT model takes comments as important auxiliary features and masks coattention between posts and comments on lower-layers. Experiments on Weibo20 and three existing social media datasets showed that STANKER outperformed all compared models, especially beating the old state-of-theart on Weibo dataset.

show abstract

Modeling Conversation Structure and Temporal Dynamics for Jointly Predicting Rumor Stance and Veracity

Cited by 55 publications

References 45 publications

A Weakly Supervised Propagation Model for Rumor Verification and Stance Detection with Multiple Instance Learning

A Weakly Supervised Propagation Model for Rumor Verification and Stance Detection with Multiple Instance Learning

A Stochastic Attention CNN Model for Rumor Stance Classification

STANKER: Stacking Network based on Level-grained Attention-masked BERT for Rumor Detection on Social Media

Contact Info

Product

Resources

About