Modeling the spread of fake news on Twitter

Competing social contagions with opinion-dependent infectivity

The spread of disinformation (maliciously spread false information) in online social networks has become an important problem in today's society. Disinformation's spread is facilitated by the fact that individuals often accept false information based on cognitive biases which predispose them to believe information that they have heard repeatedly or that aligns with their beliefs. Moreover, disinformation often spreads in direct competition with corresponding true information. To model these phenomena, we develop a model for two competing beliefs spreading on a social network, where individuals have an internal opinion that models their cognitive biases and modulates their likelihood of adopting one of the competing beliefs. By numerical simulations of an agent-based model and a mean-field description of the dynamics, we study how the long-term dynamics of the spreading process depend on the initial conditions for the number of spreaders and the initial opinion of the population. We find that the addition of cognitive biases enriches the transient dynamics of the spreading process, facilitating behavior such as the revival of a dying belief and the overturning of an initially widespread opinion. Finally, we study how external recruitment of spreaders can lead to the eventual dominance of one of the two beliefs.

Perception of misinformation on social media among Chinese college students

Background

Chinese college students predominantly use social media applications to collect information, communicate with each other, advance their education, and go shopping. Research has highlighted the spread of misinformation or fake news on social media, and this has affected college students negatively as they are the most frequent users of social media.

Objective

This research aims to investigate Chinese college students' perceptions of misinformation on social media, including their views on the consequences of misinformation, insights into the reasons for its dissemination, how misinformation impacts their mental health, and their perspectives on how to control misinformation.

Methods

This study followed a qualitative approach, selecting 36 participants from 12 universities in China, collecting data through semi-structured interviews, and analyzing the data to enable thematic analysis.

Results

Chinese college students are aware of the adverse impact of spreading misinformation on social media. They believe that false information is disseminated primarily due to inadequate punishment for those who intentionally spread it. Most college students lack proficiency in identifying misinformation, and they expect the government to do more to control the misinformation phenomenon. Moreover, misinformation on social media may cause Chinese college students to feel dysphoric, angry, and even depressed, thereby affecting their mental health. This research indicates that the public and government should make efforts to address the misinformation phenomenon in order to protect college students from being harmed.

Dynamics and characteristics of misinformation related to earthquake predictions on Twitter

The spread of misinformation on social media can lead to inappropriate behaviors that can make disasters worse. In our study, we focused on tweets containing misinformation about earthquake predictions and analyzed their dynamics. To this end, we retrieved 82,129 tweets over a period of 2 years (March 2020-March 2022) and hand-labeled 4157 tweets. We used RoBERTa to classify the complete dataset and analyzed the results. We found that (1) there are significantly more not-misinformation than misinformation tweets; (2) earthquake predictions are continuously present on Twitter with peaks after felt events; and (3) prediction misinformation tweets sometimes link or tag official earthquake notifications from credible sources. These insights indicate that official institutions present on social media should continuously address misinformation (even in quiet times when no event occurred), check that their institution is not tagged/linked in misinformation tweets, and provide authoritative sources that can be used to support their arguments against unfounded earthquake predictions.

Best Practices for Ethical Conduct of Misinformation Research

Abstract. Misinformation can have noxious impacts on cognition, fostering the formation of false beliefs, retroactively distorting memory for events, and influencing reasoning and decision-making even after it has been credibly corrected. Researchers investigating the impacts of real-world misinformation are therefore faced with an ethical issue: they must consider the immediate and long-term consequences of exposing participants to false claims. In this paper, we first present an overview of the ethical risks associated with real-world misinformation. We then report results from a scoping review of ethical practices in misinformation research. We investigated (1) the extent to which researchers report the details of their ethical practices, including issues of informed consent and debriefing, and (2) the specific steps that researchers report taking to protect participants from the consequences of misinformation exposure. We found that fewer than 30% of misinformation papers report any debriefing, and almost no authors assessed the effectiveness of their debriefing procedure. Building on the findings from this review, we evaluate the balance of risk versus reward currently operating in this field and propose a set of guidelines for best practices. Our ultimate goal is to allow researchers the freedom to investigate questions of considerable scientific and societal impact while meeting their ethical obligations to participants.

Strategies for checking misinformation: An approach from the Global South

The manipulation of information to suit one’s vested interests is a growing hazard. It has elements of disinformation, misinformation and fake news, and lacks authenticity. Such manipulation and distortion of facts can have serious consequences for a community, especially in a diverse nation like India. It calls for strict measures and awareness to check this spread. Technology further catalyses such dissemination. Institutions, libraries, governments and the media are all deliberating effective means to distinguish fake news from authentic news. This article details some such initiatives. It discusses the Government of India’s Information Technology (Intermediary Guidelines and Digital Media Ethics Code) Rules, 2021, to curb such deceitful dissemination, elements of which can be replicable in other geographies. It spotlights the issue and underscores the need for media and information literacy for all to be more discerning during the reception, consumption and assimilation of information before responding to it. Further, the fact-checking initiatives and Information Technology Rules as taken and framed in India may be replicated in other countries.

Using Social Media to Detect Fake News Information Related to Product Marketing: The FakeAds Corpus

Nowadays, an increasing portion of our lives is spent interacting online through social media platforms, thanks to the widespread adoption of the latest technology and the proliferation of smartphones. Obtaining news from social media platforms is fast, easy, and less expensive compared with other traditional media platforms, e.g., television and newspapers. Therefore, social media is now being exploited to disseminate fake news and false information. This research aims to build the FakeAds corpus, which consists of tweets for product advertisements. The aim of the FakeAds corpus is to study the impact of fake news and false information in advertising and marketing materials for specific products and which types of products (i.e., cosmetics, health, fashion, or electronics) are targeted most on Twitter to draw the attention of consumers. The corpus is unique and novel, in terms of the very specific topic (i.e., the role of Twitter in disseminating fake news related to production promotion and advertisement) and also in terms of its fine-grained annotations. The annotation guidelines were designed with guidance by a domain expert, and the annotation is performed by two domain experts, resulting in a high-quality annotation, with agreement rate F-scores as high as 0.815.

From agent-based models to the macroscopic description of fake-news spread: the role of competence in data-driven applications

Fake news spreading, with the aim of manipulating individuals' perceptions of facts, is now recognized as a major problem in many democratic societies. Yet, to date, little has been understood about how fake news spreads on social networks, what the influence of the education level of individuals is, when fake news is effective in influencing public opinion, and what interventions might be successful in mitigating their effect. In this paper, starting from the recently introduced kinetic multi-agent model with competence by the first two authors, we propose to derive reduced-order models through the notion of social closure in the mean-field approximation that has its roots in the classical hydrodynamic closure of kinetic theory. This approach allows to obtain simplified models in which the competence and learning of the agents maintain their role in the dynamics and, at the same time, the structure of such models is more suitable to be interfaced with data-driven applications. Examples of different Twitter-based test cases are described and discussed.

On the effectiveness of communication strategies as non-pharmaceutical interventions to tackle epidemics

When pharmaceutical interventions are unavailable to deal with an epidemic outbreak, adequate management of communication strategies can be key to reduce the contagion risks. On the one hand, accessibility to trustworthy and timely information, whilst on the other, the adoption of preventive behaviors may be both crucial. However, despite the abundance of communication strategies, their effectiveness has been scarcely evaluated or merely circumscribed to the scrutiny of public affairs. To study the influence of communication strategies on the spreading dynamics of an infectious disease, we implemented a susceptible-exposed-infected-removed-dead (SEIRD) epidemiological model, using an agent-based approach. Agents in our systems can obtain information modulating their behavior from two sources: (i) through the local interaction with other neighboring agents and, (ii) from a central entity delivering information with a certain periodicity. In doing so, we highlight how global information delivered from a central entity can reduce the impact of an infectious disease and how informing even a small fraction of the population has a remarkable impact, when compared to not informing the population at all. Moreover, having a scheme of delivering daily messages makes a stark difference on the reduction of cases, compared to the other evaluated strategies, denoting that daily delivery of information produces the largest decrease in the number of cases. Furthermore, when the information spreading relies only on local interactions between agents, and no central entity takes actions along the dynamics, then the epidemic spreading is virtually independent of the initial amount of informed agents. On top of that, we found that local communication plays an important role in an intermediate regime where information coming from a central entity is scarce. As a whole, our results highlight the importance of proper communication strategies, both accurate and daily, to tackle epidemic outbreaks.

Deceptive Online Content Detection Using Only Message Characteristics and a Machine Learning Trained Expert System

This paper considers the use of a post metadata-based approach to identifying intentionally deceptive online content. It presents the use of an inherently explainable artificial intelligence technique, which utilizes machine learning to train an expert system, for this purpose. It considers the role of three factors (textual context, speaker background, and emotion) in fake news detection analysis and evaluates the efficacy of using key factors, but not the inherently subjective processing of post text itself, to identify deceptive online content. This paper presents initial work on a potential deceptive content detection tool and also, through the networks that it presents for this purpose, considers the interrelationships of factors that can be used to determine whether a post is deceptive content or not and their comparative importance.

Stiffness Analysis to Predict the Spread Out of Fake Information

This work highlights how the stiffness index, which is often used as a measure of stiffness for differential problems, can be employed to model the spread of fake news. In particular, we show that the higher the stiffness index is, the more rapid the transit of fake news in a given population. The illustration of our idea is presented through the stiffness analysis of the classical SIR model, commonly used to model the spread of epidemics in a given population. Numerical experiments, performed on real data, support the effectiveness of the approach.