Network Rumor Research Articles

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.

Harmfulness metrics in digital twins of social network rumors detection in cloud computing environment

Social network rumor harm metric is a task to score the harm caused by a rumor by analyzing the spreading range of the rumor, the users affected, the repercussions caused, etc., and then the harm caused by the rumor. Rumor hazard metric models can help rumor detection digital twins to understand and analyze user behaviors and assist social network network managers to make more informed decisions. However, there is a lack of models that can quantify the harm of rumors and automated harm metric models in rumor detection digital twins. To address this issue, this paper proposes an innovative social network rumor harm metric based on rumor propagation knowledge and a large language model (LLM), RSK-T5. The method first completes the joint task of rumor comment stance detection and sentiment analysis to capture critical features of rumor propagation. Then, this knowledge is used in the pre-training process of LLM to improve the model's understanding of rumor propagation patterns. Finally, the fine-tuning phase focuses on the hazard metrics task to improve the generalization energy. We compare with some existing variants of rumor detection methods, and experimental results demonstrate that RSK-T5 achieves the lowest MSE scores on three well-known rumor detection datasets. The ablative learning work demonstrates the effectiveness of RSK-T5's knowledge of two rumor spreads.

Governing Online Rumor: An Uncertain Intervention Timing Model for Online Rumor Propagation from the Perspective of Government

In view of different types of online rumors, when the governance institutions (government departments) intervene to achieve the least cost and the best effect is a core issue of rumor governance. Based on the perspective of the government, under the premise of limited human, material and financial resources, and considering the different impacts of government intervention opportunities on the spread of different types of rumors, this paper establishes an uncertain multi-objective network rumor transmission intervention timing model, so as to achieve the optimal allocation of government intervention opportunities for different types of online rumors, minimize the total cost and maximize the inhibition effect of rumor spreading. Then, the equivalent form of the model is given, and the model is solved. In addition, numerical experiments are conducted on three types of rumors during the COVID-19 pandemic. The experimental results show that when the types of online rumors and the focus of government departments on cost and governance effect are different, the optimal time for intervention will change. Finally, combined with the experimental results, corresponding countermeasures and suggestions are put forward for the supervision of online rumors by government departments.

The Civil Law Regulatory Path of Internet Rumor Governance in the Context of Big Data

Relying on the Internet, network rumors have the characteristics of fast spreading speed, great influence and strong harm, which will have a certain impact on people's production and life, therefore, they have also entered the vision of the government governance, but the delineation of the boundaries between the governance of network rumors and the protection of the freedom of expression has caused a lot of social controversy. At present, China's network rumor governance system faces legal dilemmas such as low legal status, legislative gaps, lagging legislation, fragmentation of the legal system, and the strong color of public law; China's network rumor governance system also faces practical dilemmas such as the difficulty of private remedies, and the impossibility of recovering the damaged reputation in a timely manner. Therefore, in order to better manage rumors, maintain the peace and stability of the country and society, and protect the immediate interests of the people, we should start from legislation and control rumors by law. Firstly, the definition of rumor should be clarified through legislation, secondly, the types and methods of punishment should be clarified through legislation, and finally, the legal system of Internet rumor management in China should be improved through multi-channel management of Internet rumors, so as to realize the grand goal of China under the rule of law.

Social Network Rumor Detection Method Combining Dual-Attention Mechanism With Graph Convolutional Network

Most rumor detection methods extract the features of rumor through two aspects of text semantics and propagation structure to achieve automatic rumor classification, while most of the existing methods do not realize that false and irrelevant interactions in the propagation structure will reduce the accuracy of rumor detection. In addition, most of the existing rumor detection methods failed to effectively extract key clues from the comments of social network users. In response to these phenomena, this article proposes a social network rumor detection method combining a dual attention mechanism and graph convolutional network (GCN) (dual-attention GCN, DA-GCN). First, build an event propagation graph; then, the GCN is used to extract the propagation structure information of each event-related microblog (tweet), and the attention mechanism is combined to suppress the false and irrelevant interactive relationships. Therefore, the anti-interference propagation structure features are extracted from the propagation graph. Second, to fully utilize the clues in users’ comments, this article makes use of the attention mechanism to fuse source microblog (tweet) with the comment–retweet information and extract interactive semantic features from it. Finally, the above two features are fused to generate a new event representation. Experimental results show that the proposed DA-GCN has an accuracy of 94.4%, 90.5%, and 90.2% on the Weibo dataset, the Twitter15 dataset, and the Twitter16 dataset, respectively, and has achieved excellent performance in the early rumor detection task, which proves that the proposed method is reasonable and effective.

Network Rumor Detection Using Attention Mechanism and BiGRU Neural Network in Big Data Environment

The research object of this paper is rumors, mainly focusing on the dissemination characteristics of rumors on Weibo platforms and conducting rumor attribute detection. Aiming at the problems of low accuracy and poor timeliness of current rumor detection methods, a network rumor detection method using attention mechanism and Gated Recurrent Unit (GRU) neural network is proposed. First, pre-processing operations such as data noise cleaning, Chinese word segmentation and stop word removal are performed on the constructed Weibo corpus data, and word vectors are obtained by using the Continuous Bag-of-Words (CBOW) model in the Word2vec neural language model. Then, the Bidirectional GRU neural network (BiGRU) is used to obtain information, combined with the structured attention mechanism to build an GRU rumor detection model. The introduction of attention mechanism makes the network model tend to grasp the text Semantic information. Finally, the Adam algorithm is used to optimize the proposed model, and the loss function of the model is constructed and minimized in combination with the binary cross-entropy loss function. The results show that the detection precision rate, recall rate, F1 value and accuracy rate of the proposed method are the largest, reaching 95.28%, 88.78%, 88.69% and 94.89%, respectively, and the detection performance is better than the other three comparison algorithms.

A novel complex social network rumor stochastic model: Convergence in distribution to a final rumor size

We introduce a chain-binomial model in a heterogeneous complex social network (HCSN) to investigate the spread of a rumor. A novel formulation of the state of the Markov chain (MC) for the SEIR (susceptible-exposed-infected-removed) rumor epidemic model is obtained, where two discrete time measures represent individuals in their disease states both instantaneously, and also the total time duration in each state. The general MC is characterized in the HCSN, for both the mean-field and global levels of the network rumor epidemic dynamics. The convergence in distribution of the MC to the final size of the rumor epidemic random variable is fully characterized. Moreover, the algorithm to obtain the expected final number of nodes that ever hear the rumor is given. An example to demonstrate the algorithm is presented.

A review of rumor detection techniques in social networks

Social networks have accelerated the speed and scope of information dissemination. However, the lack of regulation and freedom of speech on social platforms has resulted in the widespread dissemination of the unverified message. Therefore, rapid and effective detection of social network rumors is essential to purify the network environment and maintain public security. Currently, the defects of rumor detection technology are that the detection time is too long and the timeliness is poor. In addition, the differences based on specific regions or specific fields will lead to deviations in the training dataset. In this paper, firstly, the definition of rumor is described, and the current problems and detection process of rumor detection are described; Secondly, introduce different data acquisition methods and analyze their advantages and disadvantages; Thirdly, according to the development of rumor detection technology, the existing rumor detection methods of artificial, machine learning and deep learning are analyzed and compared; Finally, the challenges of social network rumor detection technology are summarized.

Uncertain comprehensive evaluation of the spreading intensity of internet rumors in the new media era

<p style='text-indent:20px;'>Rumor is a kind of abnormal information, which spreads faster than normal information, and has high transmission intensity. The existing rumor spreading formulas give an explanation of rumor spreading intensity. However, there has been a lack of corresponding research on how to measure. This paper presents a method. Firstly, the rumor spreading formula is combed and commented, and the important influencing factors in the process of rumor spreading are extracted. Secondly, the influencing factors of rumor information dissemination are analyzed, and an uncertain evaluation index list of network rumor intensity is constructed, and the dissemination intensity of rumor information is measured based on uncertain comprehensive evaluation. Finally, the effectiveness of the application of the evaluation model is verified by a numerical example, and operational policy suggestions are given according to the analysis of the results.</p>

Prediction of the Forwarding Volume of Campus Microblog Public Opinion Emergencies Using Neural Network

With the continuous expansion of colleges and universities, the proportion of college students among netizens has increased rapidly. They have become an important component of Chinese netizens and the main audience of Weibo. It is easier for online public opinion to form in some social media platforms than in others. We explain places for political conversation in Chinese cyberspace in terms of interaction, which results in various types of political discussion, based on research on authoritarian deliberation. The crisis of college network public opinion caused by the improper use of Weibo by college students occurs frequently. College network public opinion has become an important factor affecting the development and stability of colleges and universities. Social network rumor forwarding behavior refers to whether users forward specific rumors. Also, there is no surety about the truthfulness of the rumor. Taking Weibo as an example, this paper proposes a neural network-based model for predicting the forwarding volume of public opinion emergencies on campus Weibo. It solves the problem of low prediction accuracy of traditional SVM and other models. The data-driven experimental findings suggest that the technique described in this study can increase the accuracy of predicting forwarding volume in unexpected campus public opinion events.

Audience Dissemination Response Law and Action Mechanism Based on Internet Rumor Computer Big Data

Various novel Internet rumors have also emerged. This article mainly researches the audience dissemination response law and the mechanism of action. This paper constructs a model of network rumor spreading. In the homogeneous network, we know that for the rumors that the initial infection rate is large, the increase caused by the herd phenomenon is not very large. For heterogeneous networks, we need to separately examine the increase of nodes and sparse nodes in the network under different initial infection rates. With the change of time, the number of nodes in each state will change due to interaction. When an ignorant person contacts a communicator, the ignorant person will be converted into a rumor communicator with a certain probability. Affected by the memory ability of individual user nodes, each online rumor support node and online rumor opposition node becomes an online ordinary user node with a constant probability f. Affected by the rumor support node, an online ordinary user node is transformed into a receiving unread node by a rumor support node with probability β at time t. Experimental data shows that when the herd effect is not considered, it is found that the transmission peak is 0.4328 at t = 10. When the herd effect is introduced, the spread of rumors reaches the transmission peak 0.5431 at t = 8. After the introduction of the herd effect, the peak value increased by 25.5%, and the time to reach the peak was shortened by 20%. The results show that computer big data technology has a significant inhibitory effect on the spread of Internet rumors.

A Hybrid Approach for Network Rumor Detection Based on Attention Mechanism and Bidirectional GRU Model in Big Data Environment

In view of the low accuracy of Internet rumor detection in traditional machine learning detection methods due to the influence of comment directivity and incomplete features caused by too long sequences, an Internet rumor detection method combining attention mechanism and bidirectional gated recurrent unit (GRU) model in big data environment is proposed. First, the continuous bag of words (CBOW) model is modified by defining the context window and introducing the weighting module, and it is used to obtain the word vectors of the text. Then, the word vectors are used as the word embedding layer which is fed into a bidirectional GRU combined with an attention mechanism through the convolutional layer and pooling layer of the convolutional neural network (CNN) to fully extract the features of the text. Finally, the text feature vectors are input into the Softmax classifier for classification so as to realize the detection of Internet rumors. Based on the selected microblog dataset, the experimental results of the proposed model show that when the learning rate is set to 0.015, Accuracy, Precision, Recall, and F1 values are about 95.8%, 93.1%, 92.9% and 93.5%, respectively, which are better than other comparison models.

Rumor propagation dynamics in social networks under the influence of time delay and diffusion

Rumors in social networks are often referred to as infectious diseases of the Internet, because rumors spreading in networks feature strong concealment, fast transmission speed and wide spread. With the development of mobile devices, online rumors nowadays are far more harmful than before. Rumors in social networks show completely different spatiotemporal dynamics from traditional rumor spreading dynamics. A social network rumor spreading model with considering both reaction diffusion and fermentation time delay is proposed in this paper. The effects of spatial diffusion and time delay on rumor spreading in online social networks are studied. Firstly, the existence of equilibrium point of the reaction-diffusion rumor spreading model is analyzed, and the basic regeneration number <inline-formula><tex-math id="M2">\begin{document}$R_{0}$\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M2.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M2.png"/></alternatives></inline-formula> is calculated. When <inline-formula><tex-math id="M3">\begin{document}$R_{0} < 1$\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M3.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M3.png"/></alternatives></inline-formula>, the rumor stops spreading and disappears in social networks; when <inline-formula><tex-math id="M4">\begin{document}$R_{0}>1$\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M4.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M4.png"/></alternatives></inline-formula>, the rumor persists in social networks. Secondly, the local stability of the rumor spreading equilibrium is investigated by using the Roth-Hurwitz stability criterion, and the influence of diffusion on the system stability is discussed. When the diffusion is introduced into a stable rumor spreading model without time delay, the model becomes unstable, indicating that the Turing instability is caused by diffusion. Thirdly, the Hopf bifurcation condition of the rumor spreading model is established by selecting the time delay <i>τ</i> as the bifurcation parameter, and the expression of bifurcation threshold <inline-formula><tex-math id="M5">\begin{document}$\tau_{0}$\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M5.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M5.png"/></alternatives></inline-formula> is given. When <inline-formula><tex-math id="M6">\begin{document}$\tau < \tau_{0}$\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M6.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M6.png"/></alternatives></inline-formula>, the rumor propagation model with diffusion term is stable; when <inline-formula><tex-math id="M7">\begin{document}$\tau>\tau_{0}$\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M7.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M7.png"/></alternatives></inline-formula>, the model loses the stability and the Hopf bifurcation occurs. The numerical simulation results show that both diffusion and time delay play an important role in the dynamic evolution of rumor spreading. At the same time, the influence of the crowding degree of spreaders on rumor propagation is also simulated. As the crowding gets worse and worse, the rumor refuting effect weakens, the bifurcation threshold <inline-formula><tex-math id="M8">\begin{document}$\tau_{0}$\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M8.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20220726_M8.png"/></alternatives></inline-formula> decreases, and the propagation peak increases. Therefore, it is important to build an excellent social network environment to supervise the rumors that are still in the fermentation stage, improve the timeliness of the release of rumor refuting information, and strengthen the refuting of rumors among key groups. This paper breaks through the limitation considering only the time evolution, explores the spatiotemporal spreading law of rumor in real society, and provides a new perspective and idea for governing the rumor spreading.

Ways to Rectify Network Rumors in Ideological and Political Education

Network rumor is a false speech formed through network media. It not only has the false essence of traditional rumor, but also forms new characteristics under the protection of the virtual, interactive and fast characteristics of new media such as the Internet. Internet rumors, in the name of “Internet freedom”, explain the expression of public opinion, spread negative emotions and pollute the public opinion environment, which have become a serious obstacle to the ideological and political education and brought great challenges to the construction of mainstream ideology in China. In the new era, the key to how to crack down on and rectify network rumors is to promote the mainstream ideology, occupy the highland of network public opinion and purify the network environment. At the same time, using ideological and political education as a weapon to repel Internet rumors is a long-term and systematic project, which needs the restraint of law, the consciousness of the people and the responsibility of Ideological and political educators.

Multilevel Attention Residual Neural Network for Multimodal Online Social Network Rumor Detection

In recent years, with the rapid rise of social networks, such as Weibo and Twitter, multimodal social network rumors have also spread. Unlike traditional unimodal rumor detection, the main difficulty of multimodal rumor detection is in avoiding the generation of noise information while using the complementarity of different modal features. In this article, we propose a multimodal online social network rumor detection model based on the multilevel attention residual neural network (MARN). First, the features of text and image are extracted by Bert and ResNet-18, respectively, and the cross-attention residual mechanism is used to enhance the representation of images with a text vector. Second, the enhanced image vector and text vector are concatenated and fused by the self-attention residual mechanism. Finally, the fused image–text vectors are classified into two categories. Among them, the attention mechanism can effectively enhance the image representation and further improve the fusion effect between the image and the text, while the residual mechanism retains the unique attributes of each original modal feature while using different modal features. To assess the performance of the MARN model, we conduct experiments on the Weibo dataset, and the results show that the MARN model outperforms the state-of-the-art models in terms of accuracy and F1 value.

Rumor Situation Discrimination Based on Empirical Mode Decomposition Correlation Dimension

To effectively identify network rumors and block their spread, this paper uses fractal theory to analyze a network rumor spreading situation time series, reveal its inner regularity, extract features, and establish a network rumor recognition model. The model is based on an empirical mode decomposition (EMD) correlation dimension and K-nearest neighbor (KNN) approach. Firstly, a partition function is used to determine if the time series of the rumor spreading situation is a uniform fractal process. Secondly, the rumor spreading situation is subjected to EMD to obtain a series of intrinsic mode functions (IMFs), construct the IMF1–IMF6 components containing effective feature information as the principal components, and reconstruct the phase space of the principal components, respectively. Finally, the correlation dimensions of the principal components IMF1–IMF6 as obtained by the Grassberger-Procaccia algorithm are used as feature parameters and are imported into the KNN model for rumor recognition. The experimental results show that the correlation dimension of a spreading situation can better reflect the characteristic information; as combined with the KNN model for identifying rumors, the recognition rate reaches 87.5%. This result verifies the effectiveness of fractal theory in network rumors recognition, expands the thinking for the research of rumors recognition, and provides theoretical support for rumor governance.

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.

Social Network Rumor Recognition Based on Enhanced Naive Bayes

In recent years, with the increasing popularity of social networks, rumors have become more common. At present, the solution to rumors in social networks is mainly through media censorship and manual reporting, but this method requires a lot of manpower and material resources, and the cost is relatively high. Therefore, research on the characteristics of rumors and automatic identification and classification of network message text is of great significance. This paper uses the Naive Bayes algorithm combined with Laplacian smoothing to identify rumors in social network texts. The first is to segment the text and remove the stop words after the word segmentation is completed. Because of the datasensitive nature of Naive Bayes, this paper performs text preprocessing on the input data. Then a naive Bayes classifier is constructed, and the Laplacian smoothing method is introduced to solve the problem of using the naive Bayes model to estimate the zero probability in rumor recognition. Finally, experiments show that the Naive Bayes algorithm combined with Laplace smoothing can effectively improve the accuracy of rumor recognition.

Countermeasures of Internet Rumor Management Based on Artificial Intelligence Technology

With the development of The Times, the development of artificial intelligence technology with each passing day, its research and application has been widely penetrated into human daily life and scientific field, to human politics, economy, ecology, culture and other aspects of the abyss. Therefore, people must be alert to the risk of spreading online rumors brought by artificial intelligence technology. The purpose of this paper is to study the countermeasures of Internet rumor propagation under the background of artificial intelligence. This article from the perspective of risk early warning, to promote the sound development of artificial intelligence as the background, combined with the related theory foundation, in order to effectively cope with Internet rumors spread for specific research object, analyzes the present situation of Internet rumors spread, and from the technical level, national level and system level three Angle analysis how to effectively deal with Internet rumors spread, develop effectively cope with the spread of Internet rumors solutions and Suggestions, in order to in a certain extent, reduce the risk of Internet rumors transmission losses to individuals or countries. The experimental results show that the effective response to network rumor propagation can alleviate the loss caused by its risk, promote the good development of artificial intelligence technology, and build a safe and friendly network communication and information dissemination environment.

Research on behavior modeling of emergency network rumor information dissemination processing

This study presents a complete behavioral model of network rumor information dissemination. Firstly, introduces the relevant psychological characteristics of communicator information processing behavior, such as media literacy, psychological distance, cognitive resources and stereotypes. Secondly, according to the research object, communicators are classified into event-related and event-independent kinds. The basic process of information dissemination of network rumors is proposed. After that, based on the combination of psychological model, statistical learning method and opinion dynamics, the event-related and event-independent rumors communicators behaviors are quantitatively modeled. This is a preliminary study combined with psychology model and statistical learning methods, the model comes from the data and has high credibility real-time dynamics, it can be used to predict the future evolution process of network rumor, which is of great theoretical significance and practical value.