Rumor Detection Research Articles

A Rumors Detection Method Using T5-Based Prompt Learning

Accurately identifying rumor information is crucial for efficient information assessment. Pretrained Language Models (PLMs) are trained on large text data, understanding and generating human-like language patterns, and fine-tuning for specific NLP tasks. However, adjusting PLMs typically requires modifications for specific tasks, creating a gap between pretraining and task execution. Prompt learning reduces this gap. We introduce “Prompt Learning for Rumor Detection” (PLRD) based on T5, which utilizes T5-generated prompt templates to transform the detection task into a prompt-driven learning framework. Through precise prompt guidance, PLRD leverages model knowledge, enhancing rumor detection capabilities, especially in data-scarce scenarios. Experimental validation on Weibo and Twitter datasets confirms PLRD's superiority over existing methods, particularly in scenarios with limited data. Comparative analysis against state-of-the-art methods highlights PLRD's competitiveness and advancement in rumor detection.

Retraction Note: CanarDeep: a hybrid deep neural model with mixed fusion for rumour detection in social data streams

Retraction Note: CanarDeep: a hybrid deep neural model with mixed fusion for rumour detection in social data streams

Lgt: long-range graph transformer for early rumor detection

Lgt: long-range graph transformer for early rumor detection

MVACLNet: A Multimodal Virtual Augmentation Contrastive Learning Network for Rumor Detection

In today’s digital era, rumors spreading on social media threaten societal stability and individuals’ daily lives, especially multimodal rumors. Hence, there is an urgent need for effective multimodal rumor detection methods. However, existing approaches often overlook the insufficient diversity of multimodal samples in feature space and hidden similarities and differences among multimodal samples. To address such challenges, we propose MVACLNet, a Multimodal Virtual Augmentation Contrastive Learning Network. In MVACLNet, we first design a Hierarchical Textual Feature Extraction (HTFE) module to extract comprehensive textual features from multiple perspectives. Then, we fuse the textual and visual features using a modified cross-attention mechanism, which operates from different perspectives at the feature value level, to obtain authentic multimodal feature representations. Following this, we devise a Virtual Augmentation Contrastive Learning (VACL) module as an auxiliary training module. It leverages ground-truth labels and extra-generated virtual multimodal feature representations to enhance contrastive learning, thus helping capture more crucial similarities and differences among multimodal samples. Meanwhile, it performs a Kullback–Leibler (KL) divergence constraint between predicted probability distributions of the virtual multimodal feature representations and their corresponding virtual labels to help extract more content-invariant multimodal features. Finally, the authentic multimodal feature representations are input into a rumor classifier for detection. Experiments on two real-world datasets demonstrate the effectiveness and superiority of MVACLNet on multimodal rumor detection.

A Review of Machine Learning Approaches for Rumour Detection: Techniques, Challenges, and Future Directions (Machine Learning for Rumour Detection)

Rumours and misinformation propagate rapidly across online social networks, posing significant challenges to maintaining the integrity of information dissemination. In recent years, machine learning (ML) techniques have emerged as promising tools for automating the detection and mitigation of rumours. This review paper provides a comprehensive examination of the advancements in rumour detection using ML approaches. The paper begins by outlining the landscape of rumour dissemination in online social networks, highlighting the characteristics and challenges associated with rumour detection. Subsequently, it systematically categorizes and analyzes various ML methods employed for rumour detection, including supervised, unsupervised, and semi-supervised learning approaches. Furthermore, the review delves into the diverse features and representations utilized in ML models for rumour detection, such as textual content, user engagement patterns, network structures, and temporal dynamics. It discusses the strengths and limitations of different feature sets and their impact on the effectiveness of rumour detection systems. Moreover, the paper explores the intricacies of dataset construction and evaluation methodologies for training and testing rumour detection models. It examines commonly used benchmark datasets and evaluation metrics, emphasizing the importance of robust evaluation frameworks for assessing the performance of ML-based rumour detection systems accurately. Additionally, the review identifies key challenges and open research questions in the field of rumour detection using ML, including handling evolving rumour patterns, addressing adversarial attacks, and enhancing the interpretability and explain ability of ML models. It also discusses potential directions for future research aimed at advancing the state-of-the-art in rumour detection and mitigation.

Rumor detection based on Attention Graph Adversarial Dual Contrast Learning.

It is becoming harder to tell rumors from non-rumors as social media becomes a key news source, which invites malicious manipulation that could do harm to the public's health or cause financial loss. When faced with situations when the session structure of comment sections is deliberately disrupted, traditional models do not handle them adequately. In order to do this, we provide a novel rumor detection architecture that combines dual comparison learning, adversarial training, and attention filters. We suggest the attention filter module to achieve the filtering of some dangerous comments as well as the filtering of some useless comments, allowing the nodes to enter the GAT graph neural network with greater structural information. The adversarial training module (ADV) simulates the occurrence of malicious comments through perturbation, giving the comments some defense against malicious comments. It also serves as a hard negative sample to aid double contrast learning (DCL), which aims to learn the differences between various comments, and incorporates the final loss in the form of a loss function to strengthen the model. According to experimental findings, our AGAD (Attention Graph Adversarial Dual Contrast Learning) model outperforms other cutting-edge algorithms on a number of rumor detection tasks. The code is available at https://github.com/icezhangGG/AGAD.git.

Rumors detection in social networks using dynamic graph-structured bi-directional long-short term memory technique

Rumors detection in social networks using dynamic graph-structured bi-directional long-short term memory technique

A model for early rumor detection base on topic-derived domain compensation and multi-user association

In the era of rapid Internet development, social networking sites have become breeding grounds for rumors. Detecting and addressing these rumors early is crucial to mitigate the potentially devastating consequences they may bring. This paper presents an innovative model for early rumor detection to tackle the challenge posed by sparse data in the early stages of rumor outbreaks. Firstly, a content-based method for data compensation is proposed, considering the feature correlation between the original and derived topics. The method effectively matches derived topics based on the content features of the topics, thereby enriching the original domain and solving the challenge of data sparsity. Secondly, a method for constructing the network structure is proposed to tackle the issue of user association within the early topic domain. This method introduces a quantification approach to evaluate the association relationship among multiple users. By incorporating game theory to quantify user emotion, the method effectively transforms the topic domain into a multi-user relationship network with a non-Euclidean structure. Finally, leveraging the capabilities of Graph Convolutional Networks (GCN) to process non-euclidean data, a novel early rumor detection model, namely DDCA-GCN, is proposed. It combines the strategies of topic-derived domain compensation and the principle of multi-user correlation. It can effectively identify early rumors and simultaneously comprehensively analyze users’ responses. The experimental results successfully demonstrate the feasibility of incorporating derived topic elements for early rumor detection. This validation underscores the effectiveness of leveraging derived topic domains to bolster the accuracy and timeliness of rumor detection.

Nowhere to Hide: Online Rumor Detection Based on Retweeting Graph Neural Networks.

Online rumor detection is crucial for a healthier online environment. Traditional methods mainly rely on content understanding. However, these contents can be easily adjusted to avoid such supervision and are insufficient to improve the detection result. Compared with the content, information propagation patterns are more informative to support further performance promotion. Unfortunately, learning the propagation patterns is difficult, since the retweeting tree is more topologically complicated than linear sequences or binary trees. In light of this, we propose a novel rumor detection framework based on structure-aware retweeting graph neural networks. To capture the propagation patterns, we first design a novel conversion method to transform the complex retweeting tree as more tractable binary tree without losing the reconstruction information. Then, we serialize the retweeting tree as a corpus of meta-tree paths, where each meta-tree can preserve a basic substructure. A deep neural network is then designed to integrate all meta-trees and to generate the global structural embeddings. Furthermore, we propose to integrate content, users, and propagation patterns to enhance more reliable performance. To this end, we propose a novel self-attention-based retweeting neural network to learn individual features from both content and users. We then fuse the node-level features with our global structural embeddings via a mutual attention unit. In this way, we can generate more comprehensive representations for rumor detection. Extensive evaluations on two real-world datasets show remarkable superiorities of our model compared with existing methods.

Topic to Image: A Rumor Detection Method Inspired by Image Forgery Recognition Technology

Topic to Image: A Rumor Detection Method Inspired by Image Forgery Recognition Technology

Rumor Detection with A Novel Graph Neural Network Approach

The wide spread of rumors[3] on social media has caused a negative impact on people's daily life, leading to potential panic, fear and mental health problems for the public.[47] How to debunk rumors as early as possible remains a challenging problem. Existing studies mainly leverage information propagation structure to detect rumors[6], while very few works focus on correlation among users that they may coordinate to spread rumors in order to gain a large popularity. In this paper, we propose a new detection model, that jointly learns both the representations of user correlation and information propagation to detect rumors on social media. Specifically, we leverage graph neural networks to learn the representations of user correlation from a bipartite graph[5] that describes the correlations between users and source tweets[12], and the representations of information propagation with a tree structure. Then we combine the learned representations from these two modules to classify the rumors. Since malicious users intend to subvert our model after deployment, we further develop a greedy attack scheme to analyze the cost of three adversarial attacks: graph attack, comment attack and joint attack. Evaluation results on two public datasets illustrate that the proposed MODEL outperforms the state-of-the-art rumor detection models. We also demonstrate our method performs well for early rumor detection.[8] Moreover, the proposed detection method is more robust to adversarial attacks compared to the best existing method. Importantly, we show that it requires high cost for attackers to subvert user correlation pattern, demonstrating the importance of considering user correlation for rumor detection.

Frequency Spectrum Is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor Detector

Multimodal content, such as mixing text with images, presents significant challenges to rumor detection in social media. Existing multimodal rumor detection has focused on mixing tokens among spatial and sequential locations for unimodal representation or fusing clues of rumor veracity across modalities. However, they suffer from less discriminative unimodal representation and are vulnerable to intricate location dependencies in the time-consuming fusion of spatial and sequential tokens. This work makes the first attempt at multimodal rumor detection in the frequency domain, which efficiently transforms spatial features into the frequency spectrum and obtains highly discriminative spectrum features for multimodal representation and fusion. A novel Frequency Spectrum Representation and fUsion network (FSRU) with dual contrastive learning reveals the frequency spectrum is more effective for multimodal representation and fusion, extracting the informative components for rumor detection. FSRU involves three novel mechanisms: utilizing the Fourier transform to convert features in the spatial domain to the frequency domain, the unimodal spectrum compression, and the cross-modal spectrum co-selection module in the frequency domain. Substantial experiments show that FSRU achieves satisfactory multimodal rumor detection performance.

Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning Approach for Rumor Detection

Rumor detection on social media has become increasingly important. Most existing graph-based models presume rumor propagation trees (RPTs) have deep structures and learn sequential stance features along branches. However, through statistical analysis on real-world datasets, we find RPTs exhibit wide structures, with most nodes being shallow 1-level replies. To focus learning on intensive substructures, we propose Rumor Adaptive Graph Contrastive Learning (RAGCL) method with adaptive view augmentation guided by node centralities. We summarize three principles for RPT augmentation: 1) exempt root nodes, 2) retain deep reply nodes, 3) preserve lower-level nodes in deep sections. We employ node dropping, attribute masking and edge dropping with probabilities from centrality-based importance scores to generate views. A graph contrastive objective then learns robust rumor representations. Extensive experiments on four benchmark datasets demonstrate RAGCL outperforms state-of-the-art methods. Our work reveals the wide-structure nature of RPTs and contributes an effective graph contrastive learning approach tailored for rumor detection through principled adaptive augmentation. The proposed principles and augmentation techniques can potentially benefit other applications involving tree-structured graphs.

A Bi-GRU-DSA-based social network rumor detection approach

Abstract In the rumor detection based on crowd intelligence, the crowd behavior is constructed as a graph model or probability mode. The detection of rumors is achieved through the collaborative utilization of data and knowledge. Aiming at the problems of insufficient feature extraction ability and data redundancy of current rumor detection methods based on deep learning model, a social network rumor detection method based on bidirectional gated recurrent unit (Bi-GRU) and double self-attention (DSA) mechanism is suggested. First, a combination of application program interface and third-party crawler approach is used to obtain microblogging data from publicly available fake microblogging information pages, including both rumor and non-rumor information. Second, Bi-GRU is used to capture the tendency of medium- and long-term dependence of data and is flexible enough to deal with variable length input. Finally, the DSA mechanism is introduced to help reduce the redundant information in the dataset, thereby enhancing the model’s efficacy. The results of the experiments indicate that the proposed method outperforms existing advanced methods by at least 0.114, 0.108, 0.064, and 0.085 in terms of accuracy, precision, recall, and F1-scores, respectively. Therefore, the proposed method can significantly enhance the ability of social network rumor detection.

Security issues of news data dissemination in internet environment

With the rise of artificial intelligence and the development of social media, people's communication is more convenient and convenient. However, in the Internet environment, the untrue dissemination of news data leads to a large number of problems. Efficient and automatic detection of rumors in social platforms hence has become an important research direction in recent years. This paper leverages deep learning methods to mine the changing trend of user features related to rumor events, and designs a rumor detection model called Time Based User Feature Capture Model(TBUFCM). To obtain a new feature vector representing the user's comprehensive features under the current event, the proposed model first recomputes the user feature vector by using feature enhancement function. Then it utilizes GRU(Gate Recurrent Unit, GRU) and CNN(Convolutional Neural Networks, CNN) models to learn the global and local changes of user features, respectively. Finally, the hidden rumor features in the process of rumor propagation can be discovered by user and time information. The experimental results show that TBUFCM outperforms the baseline model, and when there are only 20 forwarded posts, it can also reach an accuracy of 92%. The proposed method can effectively solve the security problem of news data dissemination in the Internet environment.

Graph-aware multi-feature interacting network for explainable rumor detection on social network

At present, rumors are growing wantonly with the convenience and influence of social media, becoming a problem that may severely impact social stability and development. The rumor is not an objective judgment but a process of multi-dimensional subjective value superposition and a collective transaction of people’s thoughts on social networks. How to fully mine the critical features of rumor detection from the complex information of social networks is a challenge to the existing rumor detection models. Therefore, we present the explainable model GMIN (Graph-aware Multi-feature Interacting Network), aiming to fully exploit the multifaceted features of social networks by deeply analyzing the mechanism of rumor propagation and the nature of social networks. GMIN incorporates four modules to capture: the characteristics of people receiving and spreading information, the interactions and latent associations in social networks, the mechanisms of rumor propagation and diffusion, and the collaborations between various features. It is worth noting that GMIN is interpretable in the results and the model’s components. The experimental results on three real-world datasets demonstrate the validity of our proposed model and show excellent capabilities in early rumor detection and the interpretability of the model.

A novel fine-grained rumor detection algorithm with attention mechanism

Rumors circulating on social media platforms have consistently represented a substantial threat to societal security and stability. Both academia and the industry have dedicated heightened focus to addressing the issue of rumor detection. Recent research has made significant progress in using deep neural networks to model the textual content and propagation structure of rumors. However, these methods model rumor-related features at a coarse-grained level and do not take full advantage of the various contextual information associated with rumors. In this paper, we propose a new model called Hybrid Rumor Detection Model with Co-Attention Mechanisms(CoAHRD), which utilizes the original tweet content, social context information, and user information for rumor detection. First, we use the Fine-Grained Feature Learning(FGFL) algorithm to extract fine-grained features from the tweets. Based on this, we use the Graph Convolutional Network(GCN) to learn the Multi-relation graph propagation structure features of rumors. Next, we combine FGFL features with temporal encoding information to model the temporal structure of rumors. Then, we introduce a User Feature-Based Co-Attention Network(UFCoAN) to learn the tendency of different users to spread rumors. Finally, we fuse the above features through a fully connected layer and perform rumor detection. Extensive experiments on two publicly available datasets, PHEME and TWITTER15, show that our method outperforms the current mainstream methods. In particular, in terms of accuracy, our model improves by 0.9% and 1.6% over the best baseline method on the Twitter15 and PHEME datasets, respectively.

Enhancing large language model capabilities for rumor detection with Knowledge-Powered Prompting

Amid the proliferation of misinformation on social networks, automated rumor detection has emerged as a pivotal and pressing research domain. Nonetheless, current methodologies are hindered by constrained feature representations and limited adaptability in effectively addressing diverse and unconventional rumors. The incorporation of large-scale language models holds the promise of delivering heightened semantic comprehension and broader adaptability. Regrettably, prevailing general-purpose prompting approaches frequently fall short in furnishing adequate domain-specific context and guidance, thereby restricting their utility in the context of rumor detection. To ameliorate these concerns, we introduce the Knowledge-Powered Prompting strategy, which imparts task-relevant prompts and context to the model by amalgamating domain expertise with large-scale language models. This fusion equips the model to better align with the exigencies of rumor detection, mitigating the challenges posed by sensitivity to semantic subtleties and a paucity of training samples. In particular, we devise exploration prompts and bolster the prompt representation with a dynamic knowledge injection module, thereby facilitating profound reasoning about pivotal entities. Subsequently, we extract valuable external knowledge through the filtration of interactions between knowledge and claim, thereby diminishing the impact of noise. Concurrently, we undertake joint optimization, encompassing multi-task prompt population and categorical judgment objectives, fostering synergistic semantic modeling and discriminative assessments. Empirical evaluations reveal that our methodology substantially outperforms existing models.

A novel approach for rumor detection in social platforms: Memory-augmented transformer with graph convolutional networks

Rumor detection in social media platforms is of critical importance owing to the widespread dissemination and impact of false information. Conventional approaches to rumor detection frequently rely on labor-intensive manual fact-checking or handcrafted features that may not adequately account for the complex nature of rumor propagation. To overcome these limitations, recent studies in deep learning, such as the recurrent neural network-based method and natural language processing techniques, have shown promise in capturing sequential patterns and analyzing textual content. However, these approaches often overlook the valuable information embedded in the global structural characteristics of rumor propagation. Herein, we propose a novel approach, named memory-augmented Transformer with graph convolutional networks (GCNs-MT), for rumor detection on social platforms. Our model integrates long short-term memory cells and the multi-head attention mechanism in Transformers to capture local dependencies and global dependencies in the propagation of rumors. By incorporating GCNs, a powerful deep learning framework for structured data, we aim to leverage the structural information of rumor propagation for improved detection performance. Additionally, we construct a Chinese dataset encoded and embedded by pretrained word embeddings (Word2Vec and bidirectional encoder representations from transformers [BERT]) based on real-world tweets from Weibo. Extensive evaluations on self-constructed Chinese and curated benchmark English datasets demonstrate the effectiveness of GCNs-MT in detecting and combating misinformation in social media platforms. The proposed GCNs-MT framework offers a comprehensive and efficient solution for rumor detection, addressing the challenges in social platforms posed by the rapid dissemination and complex nature of rumors.

Sentence embedding to improve rumour detection performance model

<span lang="EN-US">Recently, most individuals have preferred accessing the most recent news via social media platforms like Twitter as their primary source of information. Moreover, Twitter enables users to post and distribute tweets quickly and unsupervised. As a result, Twitter has become a popular platform for disseminating false information, such as rumours. These rumours were then propagated as accurate and influenced public opinion and decision-making. The issue will arise when a decision or policy with substantial consequences is made based on rumours. To avoid the negative impacts of rumours, several researchers have attempted to detect them automatically as early as feasible. Previous studies employed supervised learning methods to identify Twitter rumours and relied on feature extraction algorithms to extract tweet content and context elements. However, manually extracting features is time-consuming and labour-intensive. To encode each tweet's sentence as a vector based on its contextual meaning, we proposed utilising Bidirectional Encoder Representation of Transformer (BERT) as a sentence embedding. We then used these vectors to train some classifier models to detect rumours. Finally, we compared the performance of BERT-based models to feature engineering-based models. We discovered that the suggested BERT-based model improved all parameters by around 10% compared to the feature engineering-based classification model.</span>