Rumor Detection Research Articles

Detecting and filtering rumor in social media using news media event

SummaryIn social media platform, many users post messages to express their interests and preferences daily. Because of its fast and easy access abundant people follow news events and there is a possibility for spreading rumor or fake news. This fake news is unverified at the time of posting. Therefore, it is necessary to detect and remove the fake news before it spread widely. Rumors or fake news are created illegally for the purpose of popularity, hike in their business or financial, and so forth, and these rumors need to be detected as easily as possible. Our proposed rumor detection method compares the social media content with news media and applies the support vector machine (SVM) as binary classification technique. Our experiments results revealed that the proposed method attained considerable improvement when compared to the existing machine learning techniques. The proposed SVM rumor detection approach attained better results of 89% precision, 64% recall, and 85% F‐measure. The experimental results proved that the proposed method will be useful for avoiding social damages caused by rumors in social media.

JUDO: Just-in-time rumour detection in streaming social platforms

Web platforms, especially social media, are facing a new and ever-evolving cyber threat operating at the information level. Their open nature allows a high velocity flow of rumours that emerge unexpectedly and spread quickly. While rumour detection has attracted many theoretical and practice studies, the timing of the detection is often neglected or not properly considered. Rumours often cause irreversible damage worldwide before being successfully detected. To address this, we approach early rumour detection from a streaming perspective. We present a just-in-time rumour detection framework that is built on top of the continuous scoring of rumour-related signals. To overcome the trade-off between timeliness and the coefficient of detection, our model treats social graphs as a data stream and computes the anomaly score of potential rumours at both the element-level and subgraph-level. This multi-level approach not only captures the propagation structure of rumours but also focuses on abnormal elements that are responsible for bootstrapping or amplifying the rumours (the ‘explore vs exploit’ effect). With extensive evaluations on our published benchmark, our model identifies rumours earlier than the baselines while achieving an even better detection coefficient.

A two-step rumor detection model based on the supernetwork theory about Weibo.

Based on the supernetwork theory, a two-step rumor detection model was proposed. The first step was the classification of users on the basis of user-based features. In the second step, non-user-based features, including psychology-based features, content-based features, and parts of supernetwork-based features, were used to detect rumors posted by different types of users. Four machine learning methods, namely, Naive Bayes, Neural Network, Support Vector Machine, and Logistic Regression, were applied to train the classifier. Four real cases and several assessment metrics were employed to verify the effectiveness of the proposed model. Performance of the model regarding early rumor detection was also evaluated by separating the datasets according to the posting time of posts. Results showed that this model exhibited better performance in rumor detection compared to five benchmark models, mainly owing to the application of the supernetwork theory and the two-step mechanism.

Multi-task Learning for Stance and Early Rumor Detection

Multi-task Learning for Stance and Early Rumor Detection

A novel rumor detection algorithm based on entity recognition, sentence reconfiguration, and ordinary differential equation network

Social media has recently become one of the most used media in the world. This has resulted in a great hotbed for the growth of rumors, as anyone can spread knowledge and opinions without confirmation. Previous works on rumor detection focused on hand-extracted features and spent less effort on text representation. In this research, a novel method for rumor detection on social media is proposed, which integrates entity recognition, sentence reconfiguration and ordinary differential equation network under a unified framework called ESODE. An entity recognition method to enhance the semantic understanding of rumor texts is used. Then, a sentence reconfiguration to improve the frequency of important words is designed. The complete feature map is established by further collecting statistical features from three aspects: linguistic features on the content of rumors, characteristics of users involved in rumor propagating, and propagation network structures. Finally, the ordinary differential equation network (ODEnet) is applied to detect rumors. Experimental results on datasets from Twitter and Weibo show that the proposed method achieves better performance than previous ones.

From rumor to genetic mutation detection with explanations: a GAN approach

Social media have emerged as increasingly popular means and environments for information gathering and propagation. This vigorous growth of social media contributed not only to a pandemic (fast-spreading and far-reaching) of rumors and misinformation, but also to an urgent need for text-based rumor detection strategies. To speed up the detection of misinformation, traditional rumor detection methods based on hand-crafted feature selection need to be replaced by automatic artificial intelligence (AI) approaches. AI decision making systems require to provide explanations in order to assure users of their trustworthiness. Inspired by the thriving development of generative adversarial networks (GANs) on text applications, we propose a GAN-based layered model for rumor detection with explanations. To demonstrate the universality of the proposed approach, we demonstrate its benefits on a gene classification with mutation detection case study. Similarly to the rumor detection, the gene classification can also be formulated as a text-based classification problem. Unlike fake news detection that needs a previously collected verified news database, our model provides explanations in rumor detection based on tweet-level texts only without referring to a verified news database. The layered structure of both generative and discriminative models contributes to the outstanding performance. The layered generators produce rumors by intelligently inserting controversial information in non-rumors, and force the layered discriminators to detect detailed glitches and deduce exactly which parts in the sentence are problematic. On average, in the rumor detection task, our proposed model outperforms state-of-the-art baselines on PHEME dataset by 26.85% in terms of macro-f1. The excellent performance of our model for textural sequences is also demonstrated by the gene mutation case study on which it achieves 72.69% macro-f1 score.

Multi-Modal Meta Multi-Task Learning for Social Media Rumor Detection

With the rapid development of social media platforms and the increasing scale of the social media data, the rumor detection task has become vitally important since the authenticity of posts cannot be guaranteed. To date, Many approaches have been proposed to facilitate the rumor detection process by utilizing the multi-task learning mechanism, which aims to improve the performance of rumor detection task by leveraging the useful information in the stance detection task. However, most of the existing approaches suffer from three limitations: (1) only focus on the textual content and ignore the multi-modal information which is key component contained in social media data; (2) ignore the difference of feature space between the stance detection task and rumor detection task, resulting in the unsatisfactory usage of stance information; (3) largely neglect the semantic information hidden in the fine-grained stance labels. Therefore, in this paper, we design a Multi-modal Meta Multi-Task Learning (MM-MTL) framework for social media rumor detection. To make use of multiple modalities, we design a multi-modal post embedding layer which considers both textual and visual content. To overcome the feature-sharing problem of the stance detection task and rumor detection task, we propose a meta knowledge-sharing scheme to share some higher meta network-layers and capture the meta knowledge behind the multi-modal post. To better utilize the semantic information hidden in the fine-grained stance labels, we employ the attention mechanism to estimate the weight of each reply. Extensive experiments on two Twitter benchmark datasets demonstrate that our proposed method achieves state-of-the-art performance.

Rumor2vec: A rumor detection framework with joint text and propagation structure representation learning

Rumors often yield adverse societal and economic impacts. Therefore, rumor detection has attracted a surge of research interests. Existing methods mainly focus on finding clues from textual contents, which is not quite effective as rumors can be intentionally manipulated. Recent studies have demonstrated that the propagation structure of rumors can significantly improve rumor detection performance. However, propagation-based methods are still limited as the propagation structure is often sparse at an early stage. In this study, we propose Rumor2vec, a novel rumor detection framework with joint text and propagation structure representation learning. First, we present the concept of the union graph to incorporate propagation structures of all tweets to mitigate the sparsity issue. Then, we leverage network embedding to learn representations of nodes in the union graph. Finally, we propose a framework for rumor representation learning and detection. Experimental results on three real-world datasets demonstrate that our proposed framework can achieve better performance than the state-of-the-art approaches. On two Twitter datasets, our method achieves 79.6% and 85.2% accuracies respectively. On the Weibo dataset, our method achieves a 95.1% accuracy. Further experiments on early rumor detection show that our method can identify rumors ahead of other methods by at least 12 h.

Rumor surveillance methods in outbreaks: A systematic literature review

Background: The spreading of health-related rumors can profoundly put society at risk, and the investigation of strategies and methods can efficiently prevent the dissemination of hazardous rumor is necessary, especially during a public health emergency including disease outbreaks. In this article we review the studies that implicated the surveillance system in identifying rumors and discuss the different aspects of current methods in this field. Methods: We searched PubMed, EMBASE, Scopus, and Web of Science databases for relevant publications in English from 2000 to 2020. The PICOS approach was used to select articles, and two reviewers extracted the data. Findings were categorized as a source of rumors, type of systems, data collection, and data transmission methods. The quality of the articles was assessed using the Mixed Method Appraisal Tool (MMAT) checklist. Results: Five studies that presented the methods used for rumor detection in different outbreaks were included in the critical appraisal process. Findings were grouped into four categories: source of rumors, type of systems, data collection, and data transmission methods. The source of rumors in most studies was media, including new social and traditional media. The most used data collection methods were human-computer interaction technique, and automatic and manual methods each were discussed in one study. Also, the data transmission method was asynchronous in the majority of studies. Conclusion: Based on our findings, the most common rumor detection systems used in the outbreaks were manual and/or human-computer methods which are considered to be time-consuming processes. Due to the ever-increasing amount of modern social media platforms and the fast-spreading of misinformation in the times of outbreaks, developing the automatically and real-time tools for rumor detection is a vital need.

Fuzzy Detection System for Rumors Through Explainable Adaptive Learning

Nowadays, rumor spreading has gradually evolved into a kind of organized behaviors, accompanied with strong uncertainty and fuzziness. However, existing fuzzy detection techniques for rumors focused their attention on supervised scenarios that require expert samples with labels for training. Thus, they are not able to well handle the unsupervised scenarios where labels are unavailable. To bridge such gap, this article proposed a fuzzy detection system for rumors through explainable adaptive learning. Specifically, its core is a graph embedding-based generative adversarial network (Graph-GAN) model. First of all, it constructs fine-grained feature spaces via graph-level encoding. Furthermore, it introduces continuous adversarial training between a generator and a discriminator for unsupervised decoding. The two-stage scheme not only solves the fuzzy rumor detection under unsupervised scenarios, but also improves robustness of the unsupervised training. Empirically, a set of experiments are carried out based on three real-world datasets. Compared with seven benchmark methods in terms of four metrics, the results of the Graph-GAN reveal a proper performance, which averagely exceeds baselines by 5–10%.

BCMM: A novel post-based augmentation representation for early rumour detection on social media

Online social media (OSM) has become a hotbed for the rapid dissemination of disinformation or rumour. Therefore, rumour detection, especially early rumour detection (ERD), is very challenging given the limited, incomplete and noisy information. Although there are some researches on earlier rumour detection, most of their studies require a larger dataset or a longer detection time span, i.e., the rumour detection efficiency needs to be improved. In this paper, we focus on a shorter detection time span which also means fewer online posts to achieve the task of ERD. We proposed a novel post-based augmentation representation approach to process post content of rumour events in the early stages of their dissemination, i.e., backward compression mapping mechanism (BCMM). In addition, we combine BCMM with gated recurrent unit (GRU) to represent post content, topology network of posts and metadata extracted from post datasets. We apply a three-layers GRU to enhance the representation of dataset within one hour after the occurrence of a social media event, i.e., BCMM-GRU. The steps are as follows: (1) we input the first-hour data into the first layer; (2) the first 40 min of data are channelled into the second layer with the output of the first layer making a full mapping to the second layer simultaneously; (3) the first 20 min of data are sent to the third layer while the output of the second layer applies a full mapping to the third layer simultaneously. The evaluation of BCMM-GRU’s performance entails applying k-fold cross-validation (CV) set-up on four available real-life rumour event datasets. The experimental results are superior to the baselines and model variants and achieve a high accuracy of 80.09% and F1-score of 80.18%.

Rumor Detection Based on SAGNN: Simplified Aggregation Graph Neural Networks

Identifying fake news on media has been an important issue. This is especially true considering the wide spread of rumors on popular social networks such as Twitter. Various kinds of techniques have been proposed for automatic rumor detection. In this work, we study the application of graph neural networks for rumor classification at a lower level, instead of applying existing neural network architectures to detect rumors. The responses to true rumors and false rumors display distinct characteristics. This suggests that it is essential to capture such interactions in an effective manner for a deep learning network to achieve better rumor detection performance. To this end we present a simplified aggregation graph neural network architecture. Experiments on publicly available Twitter datasets demonstrate that the proposed network has performance on a par with or even better than that of state-of-the-art graph convolutional networks, while significantly reducing the computational complexity.

Rumour Detection Based on Graph Convolutional Neural Net

Rumor detection is an important research topic in social networks, and lots of rumor detection models are proposed in recent years. For the rumor detection task, structural information in a conversation can be used to extract effective features. However, many existing rumor detection models focus on local structural features while the global structural features between the source tweet and its replies are not effectively used. To make full use of global structural features and content information, we propose Source-Replies relation Graph (SR-graph) for each conversation, in which every node denotes a tweet, its node feature is weighted word vectors, and edges denote the interaction between tweets. Based on SR-graphs, we propose an Ensemble Graph Convolutional Neural Net with a Nodes Proportion Allocation Mechanism (EGCN) for the rumor detection task. In experiments, we first verify that the extracted structural features are effective, and then we show the effects of different word-embedding dimensions on multiple test indices. Moreover, we show that our proposed EGCN model is comparable or even better than the current state-of-art machine learning models.

Demystifying automatic rumour detection in social networks: A review

The increase in the connectivity and availability of network has subsequently increased the use of social media. Social Media has emerged as the most readily accessible and fastest platform for updates related to events happening worldwide. The increase in the use of social media has also increased the misuse of resources for spreading unverified information generally termed as a rumour. The biggest problem in social media is the speed at which the information spreads without verifying its credibility. There has been lot of research for detection and prevention of rumours over social media. This paper focuses on presenting the present state of the art in automatic rumour detection in social networks. The paper highlights the prominent researches done in detecting these rumours in social network over the last 5 years. This paper shows both manual and automatic approaches that can be used. Also various tools have been identified which were developed for rumour detection in social media platforms. This paper shows the different available approaches that are being used and can be used in future with improvement.

GCNRDM: A Social Network Rumor Detection Method Based on Graph Convolutional Network in Mobile Computing

Mobile computing is a new technology emerging with the development of mobile communication, Internet, database, distributed computing, and other technologies. Mobile computing technology will enable computers or other information intelligent terminal devices to realize data transmission and resource sharing in the wireless environment. Its role is to bring useful, accurate, and timely information to any customer at anytime, anywhere, and to change the way people live and work. In mobile computing environment, a lot of Internet rumors hidden among the huge amounts of information communication network can cause harm to society and people’s life; this paper proposes a model of social network rumor detection based on convolution networks, the use of adjacency matrix between the nodes represent user and the relationship between the constructions of social network topology. We use a high‐order graph neural network (K‐GNN) to extract the rumor posting features. At the same time, the graph attention network (GAT) is used to extract the association features of other nodes of the network topology. The experimental results show that the method of the detection model in this paper improves the accuracy of prediction classification compared with deep learning methods such as RNN, GRU, and attention mechanism. The innovation of the paper proposes a rumor detection model based on the graph convolutional network, which lies in considering the propagation structure among users. It has a strong practical value.

Rumor Detection by Propagation Embedding Based on Graph Convolutional Network

Rumor Detection by Propagation Embedding Based on Graph Convolutional Network

Fusion of Machine learning for Detection of Rumor and False Information in Social Network

In recent years, spreading social media platforms and mobile devices led to more social data, advertisements, political opinions, and celebrity news proliferating fake news. Fake news can cause harm to networks, communications, and users and cause trust issues toward government, healthcare, or social media platforms. This inspired many researchers to implement models to detect falsified information content. But there are still many issues that need to be discussed and explored. In our paper, we introduce categories of fake news detection methods and compare these methods. After that, the promising applications for false news detection are extensively discussed in terms of fake account detection, bot detection, bullying detection, and security and privacy of social media. After all, A thorough discussion of the potential of machine learning approaches for fake news detection and interventions in social networks along with the state-of-the-art challenges, opportunities, and future search prospects. This article seeks to aid the readers and researchers in explaining the motive and role of the different machine learning fusion paradigms to offer them a comprehensive realization of unexplored issues related to false information and other scenarios of social networks.

Lightweight Chain for Detection of Rumors and Fake News in Social Media

Social media has become one of the most important sources of news in our lives, but the process of validating news and limiting rumors remains an open research issue. Many researchers have suggested using Blockchain to solve this problem, but it has traditionally failed due to the large volume of data and users in such environments. In this paper, we propose to modify the structure of the Blockchain while preserving its main characteristics. We achieve this by integrating customize blockchain with the Text Mining (TM) algorithm to create a modified Light Weight chain (LWC). LWC will speed up the verification process, which is carried out through proof of good history where the nodes will have the weights according to their previous posts. Moreover, the LWC will be compatible with different applications such as verifying the authenticity of news or legal religious ruling (fatwas). In this research, we have implemented a simple model to simulate the proposed LWC for the detection of fake news and preserving the characteristics and features of the traditional Blockchain. The results on experimental data reflect the effectiveness of the proposed algorithm in establishing the chain.

Multi-modal multi-level event network for rumor detection

Multi-modal multi-level event network for rumor detection

Deep Feature Fusion for Rumor Detection on Twitter

The increasing popularity of social media has made the creation and spread of rumors much easier. Widespread rumors on social media could cause devastating damages to society and individuals. Automatically detecting rumors in a timely manner is greatly needed but also very challenging technically. In this paper, we propose a new deep feature fusion method that employs the linguistic characteristics of the source tweet text and the underlying patterns of the propagation tree of the source tweet for Twitter rumor detection. Specifically, the pre-trained Transformer-based model is applied to extract context-sensitive linguistic features from the short source tweet text. A novel sequential encoding method is proposed to embed the propagation tree of a source tweet into the vector space. A convolutional neural network (CNN) architecture is then developed to extract temporal-structural features from the encoded propagation tree. The performance of the proposed deep feature fusion method is evaluated with two public Twitter rumor datasets. The results demonstrate that the proposed method achieves significantly better detection performance than other state-of-the-art baseline methods.