Rumor Refutation Research Articles

Research on rumor propagation and rumor refutation strategies in complex network environment

Research on rumor propagation and rumor refutation strategies in complex network environment

Dynamic analysis of the rumor propagation model with consideration of the refutation mechanism and activity rate in multiplex networks

With the development of social networks, misinformation including rumors is spreading through multiple channels, which brings many negative effects to society. The government and several Nongovernmental Organizations (NGOs) use relevant rumor rebuttal tactics to control the spread of rumors to prevent these detrimental impacts. In this paper, we consider the responses of different individuals to rumors and classify individuals into three categories: active, normal and inactive, with different activity rates for the three categories. In order to study the interaction between rumor repudiation mechanisms and rumor propagation, we propose a rumor propagation model that considers global and local rumor repudiation mechanisms as well as activity rates in multiplex networks. The upper layer represents the rumor refutation information propagation and the lower layer expresses the rumor propagation. And mean-field equations describing the dynamics of this model in multiplex networks are derived. We found that the threshold of rumor propagation is significantly affected by individual activity rates. Another interesting finding is that the global rumor refutation mechanism suppresses rumor propagation more than the local disinformation mechanism.

Who corrects misinformation online? Self-perceived media literacy and the moderating role of reflective judgment

PurposePurpose: The main purpose of the study is to understand the factors that facilitate correction behavior among individuals. In this study the authors examine the impact of self-perceived media literacy (SPML) and reflection on participants’ correction behavior.Design/methodology/approachMethods: Data for the study were collected from Amazon's MTurk using an online survey. Data were collected after a certificate of exemption was received by the Institutional Review Board in a research university in the United States (US) Qualtrics software was used to collect data. The total number of participants was 797.FindingsFindings: The findings show that although both SPML and reflection are positively associated with rumor refutation, higher SPML alone is not enough. Reflective judgment is critical for individuals to take part in this behavior online, such that individuals with higher reflective judgment indicated that they refute rumors online, irrespective of their SPML score.Originality/valueOriginality: The authors tested the relationship of multiple variables with participants correction behavior. Although research shows the importance of social correction, there is not much knowledge about what facilitates actual misinformation correction.

Rumor propagation in two-layer complex networks

With the development of information networks, the study on rumor propagation attracts more and more attention. In this paper, we investigate rumor propagation in two-layer complex networks with three groups of agents: spreaders, ignorants, and refuters. Considering that rumor spreading and rumor refutation are realized in different ways in real life, we assume that rumor spreads in ER layer while it is refuted in SF layer. There are three types of states in the evolution of the system after a period of transient time: 1) all individuals become refuters; 2) ignorants coexist with refuters; 3) three types of individuals coexist. The simulation results demonstrate that high refuting rate and slow spreading rate exert positive effect on the coexistence state in which spreaders, ignorants, and refuters coexist. We discuss the effects of propagation model parameters, initial densities of different agents and the topological properties of networks on the rumor propagation. We find that the probability of an agent becoming a spreader is determined by his neighbors in the SF layer. The deciding factor is the sum of degrees in the ER layer of these neighbors.

Dynamics of a stochastic epidemic-like rumor propagation model with generalized nonlinear incidence and time delay

Rumors are abnormal children of public opinion, they usually arise with environmental crisis and have serious negative functions. Hence, how to control rumor propagation has become an urgent topic for the government. Since the communication between people in the real world is inevitably interfered by random factors, and time delay exists in the process of rumor propagation not only influence rumor-forwarding individuals by rumor-hesitant individuals but also in government decision-making. Based on these premises, we propose a stochastic delayed rumor propagation model with generalized incidence function. By setting the suitable Lyapunov functions, we show that the asymptotic behavior of stochastic rumor spreading model is constrained by some conditions. Finally, our analytical results are supported by numerical simulations. The results show that (1) the increase of noise intensity in social environment will reduce rumor propagation; (2) time delay has an impact on rumor propagation to a certain extent. Extending the thinking time may reduce the number of rumor-forwarding individuals and even lead to the disappearance of rumors; (3) improve scientific literacy and accelerate rumor refutation (i.e. reduce the value of β), strengthen rumor suppression (i.e. increase the value of γ) can effectively control rumor transmission.

Configurational patterns for COVID-19 related social media rumor refutation effectiveness enhancement based on machine learning and fsQCA

Infodemics are intertwined with the COVID-19 pandemic, affecting people's perception and social order. To curb the spread of COVID-19 related false rumors, fuzzy-set qualitative comparative analysis (fsQCA) is used to find configurational pathways to enhance rumor refutation effectiveness. In this paper, a total of 1,903 COVID-19 related false rumor refutation microblogs on Sina Weibo are collected by a web crawler from January 1, 2022 to April 20, 2022, and 10 main conditions affecting rumor refutation effectiveness index (REI) are identified based on “three rules of epidemics”. To reduce data redundancy, five ensemble machine learning models are established and tuned, among which Light Gradient Boosting Machine (LGBM) regression model has the best performance. Then five core conditions are extracted by feature importance ranking of LGBM. Based on fsQCA with the five core conditions, REI enhancement can be achieved through three different pathway elements configurations solutions: “Highly influential microblogger * high followers’ stickiness microblogger”, “high followers’ stickiness microblogger * highly active microblogger * concise information description” and “high followers’ stickiness microblogger * the sentiment tendency of the topic * concise information description”. Finally, decision-making suggestions for false rumor refutation platforms and new ideas for improving false rumor refutation effectiveness are proposed. The innovation of this paper reflects in exploring the REI enhancement strategy from the perspective of configuration for the first time.

Lifecycle research of social media rumor refutation effectiveness based on machine learning and visualization technology

Rumor refutation is a common method to control rumors to address potential risks. This paper studies the social media rumor refutation effectiveness lifecycle (SMRREL), focusing on three important characteristics (i.e., lifespan, peak value, and distribution) to provide support for (1) enhancing the persistence and intensity of rumor refutation effectiveness and (2) investigating the changing law of rumor refutation effectiveness. In total, 77,080 comment records, 55,847 forward records, and other pertinent data of 251 rumor refutation microblogs from an official rumor refutation platform are collected to perform analysis. To explore how the lifespan and peak value of SMRREL are influenced by the possible affecting factors, five regressors (i.e., RFRegressor, AdaBoostRegressor, XGBoostRegressor, LGBMRegressor, and CatBoostRegressor) are trained based on the collected data. The XGBoostRegressor shows the best performance, and the results are shown and explained using SHapley Additive exPlanations (SHAP). To investigate the distribution of SMRREL, lifecycle graphs of rumor refutation effectiveness are summarized and divided into three types, i.e., Outburst, Multiple Peaks, and Steep Slope. Finally, based on the results of the SMRREL analysis, corresponding decision-making recommendations are proposed to make better persistence and intensity of rumor refutation effectiveness.

A Hybrid Clustered SFLA-PSO algorithm for optimizing the timely and real-time rumor refutations in Online Social Networks

Currently, the popularity of various social media platforms has made convenient communications and prompt information spreading in Online Social Networks (OSNs). However, it brings a serious threat to social stability and public safety when information is identified as false, misleading or inappropriate. Therefore, it is valuable that the timely and real-time rumor refutations are respectively studied to promptly and continually block the rumor spreading. Existing works on the rumor refutations are lacking in sufficient decomposition on the trust mechanism and ignore the analysis of continual blocking the rumor spreading. Motivated by these issues, this paper proposes a comprehensive Hybrid Clustered Shuffled Frog-Leaping Algorithm-Particle Swarm Optimization (HCSFLA-PSO) algorithm for promptly and continually blocking the rumor spreading in OSNs. Firstly, by making decomposition of social relations and analyzing degree of intimacy, self-reliability and credibility, a new trust mechanism of rumor refutations and a novel expression of trust degree are proposed. Secondly, a comprehensive HCSFLA-PSO algorithm is proposed by taking advantage of the clustered local search capability of the SFLA and the fast-convergence of the PSO algorithm collaborative for the rumor refutations, which includes CNP-HCSFLA-PSO sub-algorithm for the timely rumor refutation and CP-HCSFLA-PSO sub-algorithm for the real-time rumor refutation during the truth evolution according to different social relations with different trust degrees. Thirdly, a new concept of timeliness of information and a novel energy consumption model are proposed to solve the influence problem of continual updated truths. Finally, numerical simulations and ablation experiments are conducted to verify the effectiveness of our proposed algorithm.

Health-Related Rumor Control through Social Collaboration Models: Lessons from Cases in China during the COVID-19 Pandemic.

Widely spread health-related rumors may mislead the public, escalate social panic, compromise government credibility, and threaten public health. Social collaboration models that maximize the functions and advantages of various agents of socialization can be a promising way to control health-related rumors. Existing research on health-related rumors, however, is limited in studying how various agents collaborate with each other to debunk rumors. This study utilizes content analysis to code the text data of health-related rumor cases in China during the COVID-19 pandemic. The study found that socialized rumor-debunking models could be divided into the following five categories: the government-led model, the media-led model, the scientific community-led model, the rumor-debunking platform-led model, and the multi-agent collaborative model. In addition, since rumors in public health crises often involve different objects, rumor refutation requires various information sources; therefore, different rumor-debunking models apply. This study verifies the value of socialized collaborative rumor debunking, advocates and encourages the participation of multiple agents of socialization and provides guidance for establishing a collaborative rumor-debunking model, thereby promoting efficient rumor-debunking methods and improving the healthcare of society.

An ICDRI rumor propagation model based on the individual discrepancy theory in social networks

Rumors can bring about a seriously negative impact on all respects of society in this information era. More targeted control strategies can be acquired through the research of rumor propagation. When receiving rumors, individuals may keep imperturbable according to their rationality or bygone experience, and then choose not to propagate rumors provisionally. Oppositely, others may ask people around them about the realness of rumors due to bewilderment, which may further lead to the propagation of rumors. Therefore, an Ignorant–Conservative–Disseminator–Restorer–Ignorant (ICDRI) rumor dissemination model is proposed, which comprehensively considers users’ various probable actions under rumor and anti-rumor information. Furthermore, new links are added among nodes in accordance with the individual discrepancy theory and the influencing factors of rumor spreading including negation factor, authority factor, exhaustion factor, etc. According to the calculated basic regeneration number, simulation analysis and model comparison, the steady state and superiority of the ICDRI model is proved. Finally, strategies to control the spread of rumors are obtained through the sensitivity analysis of parameters. The simulation results demonstrate that the ICDRI model can more realistically reflect the dissemination of rumors, and the official rumor refutation or circular can efficaciously curb the spreading of rumors.

A Study on the Effectiveness of Rumor Control via Social Media Networks to Alleviate Public Panic About COVID-19.

The COVID-19 outbreak triggered a massive spread of unverified news on social media and has become a source of rumors. This paper studies the impact of a virtual rumor control center (RCC) on Weibo user behavior. The collected COVID-19 breaking news stories were divided into positive, negative, and neutral categories, while the moderating effect model was used to analyze the influence of anti-rumor on user behavior (forwarding, liking, and commenting). Our research found that rumor refuting does not directly affect user behavior but does have an indirect moderating effect. Rumor refuting has a profound impact on user forwarding behavior in cases of positive and negative news. Specifically, when the epidemic becomes more serious, the role of rumor refuting becomes critical, and vice versa. Refuting rumors reduces user willingness to forward positive or negative news, with more impact on negative news. Time lag analysis shows a significant moderation of unverified news within 72 h of refuting rumors but indicated an apparent weakening trend over time. Furthermore, we discovered non-linear feature and counter-cyclical phenomena in the moderating effect of rumor refutation.

Effect of Global and Local Refutation Mechanism on Rumor Propagation in Heterogeneous Network

In the process of rumors propagation, the behavior of individuals to propagation or refutation is not only influenced by the surrounding global environment but also the local environment. In this paper, a modified rumor propagation model is proposed considering the global and local effects of the rumor refutation mechanism and the activity rate of individuals in a heterogeneous network, and the dynamics process of the rumor propagation is derived by using the mean-field equation. Combining theoretical proving and simulation analysis, it shows that the critical threshold of rumor propagation has a great relationship with individual activity rates and global and local effects of the rumor refutation mechanism. The greater the government’s efforts to refute rumors, the lower the critical threshold of rumor propagation and the smaller the final rumor size. While relatively, people are much more likely to believe the global rumor refutation information taken with official information, local rumor refutation information has little influence on rumor propagation.

Ergodic stationary distribution of a stochastic rumor propagation model with general incidence function

In daily lives, when emergencies occur, rumors will spread widely on the internet. However, it is quite difficult for the netizens to distinguish the truth of the information. The main reasons are the uncertainty of netizens’ behavior and attitude, which make the transmission rates of these information among social network groups be not fixed. In this paper, we propose a stochastic rumor propagation model with general incidence function. The model can be described by a stochastic differential equation. Applying the Khasminskii method via a suitable construction of Lyapunov function, we first prove the existence of a unique solution for the stochastic model with probability one. Then we show the existence of a unique ergodic stationary distribution of the rumor model, which exhibits the ergodicity. We also provide some numerical simulations to support our theoretical results. The numerical results give us some possible methods to control rumor propagation. Firstly, increasing noise intensity can effectively reduce rumor propagation when . That is, after rumors spread widely on social network platforms, government intervention and authoritative media coverage will interfere with netizens’ opinions, thus reducing the degree of rumor propagation. Secondly, speed up the rumor refutation, intensify efforts to refute rumors, and improve the scientific quality of netizen (i.e., increase the value of β and decrease the value of α and γ), which can effectively curb the rumor propagation.

Differential Trust and Hierarchical Regulation: A Study of the Effectiveness of Rumor Refutation on Government Micro‐Blogs—Analysis Based on 1290 Rumor Refutation Messages

Purpose/Significance. This study aims to explore the differences in the effectiveness of rumor refutation dissemination on government micro‐blogs and to identify factors that may lead to such differences, so as to provide reference for the management of emergencies and to improve the effectiveness of rumor refutation. Methodology/Procedure. Using Octopus software to collect data from thirty government micro‐blogs, the number of retweets, likes, and comments were used as indicators of the effectiveness of refutation dissemination and different levels of government micro‐blogs were used as moderating variables to construct a regression model of the effect of content features and text features on refutation dissemination. The regression model was constructed to test the moderating effects of micro‐blog content and text features on the effectiveness of micro‐blog refutation. Results/Conclusions. The empirical results show that whether a micro‐blog is from the region or not and whether a micro‐blog has a title or not have a significant effect on the effectiveness of micro‐blog refutation dissemination. Therefore, refutation strategies such as combining layers, giving equal importance to content and form, and focusing on originality can be adopted to enhance the refutation effect of government micro‐blogs.

RETRACTED: Exploring the Dynamics of Justification in the Wake of a Rumor Outbreak on Social Media

This paper explores the dynamics of justification in the wake of a rumor outbreak on social media. Specifically, it examines the extent to which the five types of justification—descriptive argumentation, presumptive argumentation, evidentialism, truth skepticism, and epistemological skepticism—manifested in different voices including pro-rumor, anti-rumor, and doubts before and after fact-checking. Content analysis was employed on 1,911 tweets related to a rumor outbreak. Non-parametric cross-tabulation was used to uncover nuances in information sharing before and after fact-checking. Augmenting the literature which suggests the online community's susceptibility to hoaxes, the paper offers a silver lining: users are responsible enough to correct rumors during the later phase of a rumor lifecycle. This sense of public-spiritedness can be harnessed by knowledge management practitioners and public relations professionals for crowdsourced rumor refutation.

Susceptible-Infectious-Critical-Recovered rumor spreading model in social networks

As an important area of social networks, rumor spread has attracted the attention of many scholars. It aims to explore the rumor propagation, and to propose effective measures to curb the further spread of rumors. Different from some existing works, this paper believes that susceptible persons affected by rumor-refuting information will first enter the critical state, while ones who related to rumors will directly turn into the spread state. Therefore, this paper proposes a Susceptible-Infectious-Critical-Recovered (SICR) rumor model. In addition, considering that infectious persons with high levels of refuting rumors may cause emotional resonance among individuals, this model adds a connecting edge from the recovered to the infectious who are triggered by the information of refuting the rumors. First, the basic regeneration number [Formula: see text] is obtained by using the next generation matrix method. Then, the global stability of the rumor-free equilibrium [Formula: see text] and the persistence of rumor propagation are proved in detail in theoretical analysis. The simulation results show that the existence of a critical state can reduce the influence of rumors. Rumor refutation mechanism, as soon as possible to curb the spread of rumors, is an effective measure.

Spread Mechanism and Control Strategies of Rumor Propagation Model Considering Rumor Refutation and Information Feedback in Emergency Management

The rumor-free equilibrium state and rumor-endemic equilibrium state are two symmetric descriptions of the status of a system. The constant spreading of rumors would affect the smooth operation of emergency management procedures and cause unnecessary social and economic loss. To reduce the negative effect of rumor propagation, in this paper, we introduce a compartmental model of rumor propagation, which considers the rumor refutation of public and information feedback. By deriving mean-field equations that describe the dynamics of the model, we use analytical and numerical solutions of these equations to investigate the threshold and dynamics of the model in both the closed system and open system. The results imply that the initial equilibrium point is not stable and there exists a rumor-free equilibrium point; in the open system, there exists a threshold beyond which rumors can spread; the stability of the initial equilibrium point is related to the threshold R0 = (φ*α)/μ, and there exists a rumor-endemic equilibrium point. The development process of rumor propagation can be divided into four stages: latent period, progressive period, intense period, and recession period. Under the influence of population, rumor spreading can exceed the threshold readily because the migration rate μ is usually less than the proportion of ignorants without critical ability φ, and the rumor spreading process in an open system presents a fluctuating development, the rumor would not disappear in this autonomous system. Based on the analysis, we propose some measures, such as providing open and efficient information queries and exchange platforms, etc.

A Dynamic Competition and Predation Model for Rumor and Rumor-Refutation

Controlling rumors is related to the interplay between the rumor and rumor refutation, which compete to attract the unaware. And rumor refutation preys on the rumors, and try to eliminate rumors. Therefore, there is both a predatory and competitive relationship between the rumors and the rumor refutations. This paper presents a model based on biomathematics theory to describe the interplay between rumors and rumor refutations. The theoretical analysis of the differential equations elucidated three dynamic cases: rumor extinction; rumor refutation extinction; and rumor and rumor refutation coexistence. The subsequent analysis of the equilibrium stability in the three cases revealed both equilibrium stability and model instability. The haze rumor and the official haze refutation data were then crawled from Sina microblog, the rumor propagation process analyzed, an integral method employed for the model parameter estimation, and the proposed model used to estimate and forecast the haze rumor and rumor-refutation evolutions. The findings suggested that rumors and rumor refutations coexist, which was consistent with the theoretical analysis of coexistence. Based on this case and to more deeply analyze the effect of an authority's credibility and the public's cognition, the proposed model was used to suggest several scenarios, and policy suggestions given to assist authorities better manage rumors in emergency events.

Social media rumor refutation effectiveness: Evaluation, modelling and enhancement

Motivated by the practical needs of enhancing social media rumor refutation effectiveness, this paper is dedicated to develop a proper rumor refutation effectiveness index (REI), identify key factors influencing REI and propose decision making suggestions for rumor refutation platforms. 298,118 pieces of comments and 185,209 pieces of the reposters’ verification status of 248 rumor refutation microblogs on Sina Weibo (the Chinese equivalent of Twitter) are collected during a 1-year period using a web crawler. To extract the text characteristics and analyze the sentiment of the rumor refutation microblogs, Natural Language Processing (NLP) approaches are applied. To explore the relationship between REI and the content and contextual factors of the rumor refutation microblogs, four regression models based on the collected data are established, namely linear regression model, Support Vector regression model (SVR), Extreme Gradient Boosting regression model (XGBoostRegressor) and Light Gradient Boosting Machine regression model (LGBMRegressor). The LGBMRegressor has the best goodness-of-fit among the compared regression models. Then, SHapley Additive exPlanations (SHAP) is employed to visualize and explain the LGBMRegressor results. Decision making suggestions for rumor refutation platforms on how to organize rumor refutation microblogs under different situations such as rumor category, author’s influence and heat of topics are proposed.

Social Media Rumor Refuter Feature Analysis and Crowd Identification Based on XGBoost and NLP

One prominent dark side of online information behavior is the spreading of rumors. The feature analysis and crowd identification of social media rumor refuters based on machine learning methods can shed light on the rumor refutation process. This paper analyzed the association between user features and rumor refuting behavior in five main rumor categories: economics, society, disaster, politics, and military. Natural language processing (NLP) techniques are applied to quantify the user’s sentiment tendency and recent interests. Then, those results were combined with other personalized features to train an XGBoost classification model, and potential refuters can be identified. Information from 58,807 Sina Weibo users (including their 646,877 microblogs) for the five anti-rumor microblog categories was collected for model training and feature analysis. The results revealed that there were significant differences between rumor stiflers and refuters, as well as between refuters for different categories. Refuters tended to be more active on social media and a large proportion of them gathered in more developed regions. Tweeting history was a vital reference as well, and refuters showed higher interest in topics related with the rumor refuting message. Meanwhile, features such as gender, age, user labels and sentiment tendency also varied between refuters considering categories.