Memory -dependent fake news dissemination and control: A fractional SVEIR model with stability analysis

Online social networks (OSNs) have become an integral mode of communication among people and even nonhuman scenarios can also be integrated into OSNs. The ever-growing rise in the popularity of OSNs can be attributed to the rapid growth of Internet technology. OSN becomes the easiest way to broadcast media (news/content) over the Internet. In the wake of emerging technologies, there is dire need to develop methodologies, which can minimize the spread of fake messages or rumors that can harm society in any manner. In this article, a model is proposed to investigate the propagation of such messages currently coined as fake news. The proposed model describes how misinformation gets disseminated among groups with the influence of different misinformation refuting measures. With the onset of the novel coronavirus-19 pandemic, dubbed COVID-19, the propagation of fake news related to the pandemic is higher than ever. In this article, we aim to develop a model that will be able to detect and eliminate fake news from OSNs and help ease some OSN users stress regarding the pandemic. A system of differential equations is used to formulate the model. Its stability and equilibrium are also thoroughly analyzed. The basic reproduction number ( $R_{0}$ ) is obtained which is a significant parameter for the analysis of message spreading in the OSNs. If the value of $R_{0}$ is less than one ( $R_{0} ), then fake message spreading in the online network will not be prominent, otherwise if $R_{0}> 1$ the rumor will persist in the OSN. Real-world trends of misinformation spreading in OSNs are discussed. In addition, the model discusses the controlling mechanism for untrusted message propagation. The proposed model has also been validated through extensive simulation and experimentation.

Due to the fast advancement of Internet technology, the popularity of Online Social Networks (OSN) over the Internet is increasing day by day. In the modern world, people are using OSN to communicate with others around the world who may or may not know each other. OSN has become the most convenient means to transmit media (news/content) and gather or spread information in the world. The posts (contents) on OSN affect and impact people, and minds at least for some time. These contents are important because they play a crucial role in taking the decision. The posts which are available on the OSN may be information or just misinformation. The misinformation may be a type of fake news or rumour. This is very difficult for people to differentiate whether the posts are information or rumour. Therefore, the development of techniques that can prevent the transmission of false information or rumours that might harm society in any way is critical. In this paper, a model is developed based on the epidemic approach, for examining and controlling fake information dissemination in OSN. The proposed model illustrates how different misinformation debunking measures impact and how misinformation spreads among different groups. In this article, we explain that the proposed model will be able to recognize and eradicate fake news from OSN. The model is written as a system of differential equations. Its equilibrium and stability are also carefully examined. The basic reproduction number ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> ) is calculated, which is an important parameter in the study of message propagation in OSN. If <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> < 1, the propagation of rumor in the OSN will be minimal; nevertheless, if <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">0</sub> > 1, the fake information/rumor will continue in OSN. The effects of disinformation of rumours in OSN in the real world are explored. In addition, the model covers the fake information/rumour dissemination control mechanism. The comparative study shows that the proposed model provides a better mechanism to prevent the dissemination of fake information in OSN in comparison to other previous models. Extensive theoretical study and computation analysis have also been used to validate the proposed model.

Recent studies have confirmed a growing trend, especially among youngsters, of using Online Social Media as favourite information platform at the expense of traditional mass media. Indeed, they can easily reach a wide audience at a high speed; but exactly because of this they are the preferred medium for influencing public opinion via so-called fake news. Moreover, there is a general agreement that the main vehicle of fakes news are malicious software robots (bots) that automatically interact with human users.In previous work we have considered the problem of tagging human users in Online Social Networks as credulous users. Specifically, we have considered credulous those users with relatively high number of bot friends when compared to total number of their social friends. We consider this group of users worth of attention because they might have a higher exposure to malicious activities and they may contribute to the spreading of fake information by sharing dubious content.In this work, starting from a dataset of fake news, we investigate the behaviour and the degree of involvement of credulous users in fake news diffusion. The study aims to: (i) fight fake news by considering the content diffused by credulous users; (ii) highlight the relationship between credulous users and fake news spreading; (iii) target fake news detection by focusing on the analysis of specific accounts more exposed to malicious activities of bots. Our first results demonstrate a strong involvement of credulous users in fake news diffusion. This findings are calling for tools that, by performing data streaming on credulous’ users actions, enables us to perform targeted fact-checking.

Fake news has recently leveraged the power and scale of online social media to effectively spread misinformation which not only erodes the trust of people on traditional presses and journalisms, but also manipulates the opinions and sentiments of the public. Detecting fake news is a daunting challenge due to subtle difference between real and fake news. As a first step of fighting with fake news, this paper characterizes hundreds of popular fake and real news measured by shares, reactions, and comments on Facebook from two perspectives: Web sites and content. Our site analysis reveals that the Web sites of the fake and real news publishers exhibit diverse registration behaviors and registration timing. In addition, fake news tends to disappear from the Web after a certain amount of time. The content characterizations on the fake and real news corpus suggest that simply applying term frequency - inverse document frequency (tf-idf) and Latent Dirichlet allocation (LDA) topic modeling is inefficient in detecting fake news, while exploring document similarity with the term and word vectors is a very promising direction for predicting fake and real news. To the best of our knowledge, this is the first effort to systematically study the Web sites and content characteristics of fake and real news, which will provide key insights for effectively detecting fake news on social media.

Detecting fake news over online social media via domain reputations and content understanding

Online social media plays an important role during real world events such as natural calamities, election s, social movements etc. Since the social media usage has increased, fake news has grown. The social media is often used by modifying true news or creating fake news to spread misinformation. The creation and distribution of fake news poses major threats in several respects from a national security point of view. Hence Fake news identification becomes an essential goal for enhancing the trustworthiness of the information shared on online social network. Over the period of time many researcher has used different methods, algorithms, tools and techniques to identify fake news content from online social networks. The aim of this paper is to review and examine these methodologies, different tools, browser extensions and analyze the degree of output in question. In addition, this paper discuss the general approach of fake news detection as well as taxonomy of feature extraction which plays an important role to achieve maximum accuracy with the help of different Machine Learning and Natural Language Processing algorithms. Keywords—Fake News Detection, Natural Language Processing, Online Social Network, Machine Learning, Sentiment Analysis.

Newspapers, tabloids, and magazines gave way to digital forms of the news media like blogs, social media feeds, online news platforms, and other digital media formats. Fake news refers to a type of yellow press which intentionally presents misinformation or hoaxes spreading through bothtraditional print news media and recent online social media. In recent times, as a result of the booming as a result of the growth of online social networks, various political and commercial uses of fake news been popping up in large numbers and all over the internet. With deceptive words, online social network users can get infected by this online fake news easily, which has brought about already had significant effects on offline society. A significant objective for increasing trustworthiness of information in online social networks is to identify the fake news timely. The aim of this project is investigating the principles, methodologies and algorithms for detecting fake news articles, creators and subjects from online social networks and evaluating the corresponding performance. This undertaking addresses the difficulties brought on by the mysterious characteristics of fake news and diverse connections among news articles, creators and subjects. A novel automatic is introduced in this project. Fake news credibility inference model using deep learning algorithm. based on a collection of specific and deep diffusive model is constructed by deep learning algorithms using latent features derived from the textual information. network model to simultaneously learn the representations of news articles, authors, and subjects. Index Terms: Sentiment Analysis, Deep Learning, BERT, LSTM, CNN, Natural Language Processing (NLP), News Aggregator, Emotion Detection, Performance Metrics, Text Classification.

Online Social Networks (OSNs), such as Facebook and Twitter, are popular platforms that enable users to interact and socialize through their networked devices. However, the social nature of such applications forces users to share a great amount of personal data with other users and the OSN service providers, including pictures, location check-ins, etc. Even though some OSNs offer configurable privacy controls that limit access to shared data, users might misconfigure these controls due to their complexity or lack of clear instructions. Furthermore, the fact that OSN service providers have full access over the data stored on their servers is an alarming thought, especially for users who are conscious about their privacy. For example, OSNs might share such data with third parties, data mine them for targeted advertisements, collect statistics, etc. As a result, data and communication privacy over OSNs is a popular topic in the data privacy research community. Existing solutions include cryptographic mechanisms [1], trusted third parties [2], external dictionaries [3], and steganographic techniques [4]. Nevertheless, none of the aforementioned approaches offers a comprehensive solution that (i) implements fine-grained access control over encrypted data and (ii) works seamlessly over existing OSN platforms. To this end, we will design and implement a flexible and user-friendly system that leverages encryption-based access control and allows users to assign arbitrary decryption privileges to every data object that is posted on the OSN servers. The decryption privileges can be assigned on the finest granularity level, for example, to a hand-picked group of users. In addition, data decryption is performed automatically at the application layer, thus enhancing the overall experience for the end-user. Our cryptographic-based solution leverages hidden vector encryption (HVE)[5], which is a ciphertext policy-based access control mechanism. Under HVE, each user generates his/her own master key (one-time) that is subsequently used to generate a unique decryption key for every user with whom they share a link in the underlying social graph. Moreover, during the encryption process, the user interactively selects a list of friends and/or groups that will be granted decryption privileges for that particular data object. To distribute the decryption keys, we utilize an untrusted database server where users have to register before using our system. The server stores (i) the social relationships of the registered users, (ii) their public keys, and (iii) the HVE decryption keys assigned to each user. As the database server is untrusted, the decryption keys are stored in encrypted form, i.e., they are encrypted with the public key of the underlying user. Therefore, our solution relies on the existing public key infrastructure (PKI) to ensure the integrity and authenticity of the users’ public keys. To facilitate the deployment of our system over existing OSN platforms, we use steganographic techniques [6] to hide the encrypted data objects within randomly chosen cover images (stego images). The stego images are then uploaded to the OSN servers, and only authorized users (with the correct decryption keys) would be able to extract the embedded data. Unauthorized users will simply see the random cover images. We aim to implement our system as a Chrome-based browser extension where, after installation, the user registers with the un- trusted server and uploads/downloads the necessary decryption keys. The keys are also stored locally, in order to provide a user-friendly interface to share private information. Specifically, our system will offer a seamless decryption process, where all hidden data objects are displayed automatically while surfing the OSN platform, without any user interaction.

Fake news and online rumors can mislead information, disrupt order, and destabilize society. This misleading information is propagated through online social media and other digital platforms, which results in loss of public confidence, stimulation of social unrest, and a threat to national security. In this work, we present a Gated Recurrent Unit-based fake news recognition approach to reduce the impact of misinformation. Since we want to build an effective model, we pre-process a fake-news-detection dataset having real and fake news by performing effective natural language processing (NLP) tasks such as news text cleaning, tokenization, word embedding, etc. The Gated Recurrent Unit (GRU) architecture is used based on its ability to execute sequential data, which allows the model to find patterns and the semantic relations within news content. The model proposed attained an accuracy of 99.55% and proved to be effective for detecting fake information. Our recommendation is to continue the fight against misinformation and other such cybercrimes.

Although considerable amount of work has been conducted recently of how to predict links between users in online social media, studies inducing features from different domain data are rare. In this paper we present the latest results of a project that studies the extent to which interactions – in our case directed and bi-directed message communication – between users in online social networks can be predicted by looking at features obtained from online and location-based social network data. To that end, we conducted a number of experiments on data obtained from the virtual world of Second Life. As our results reveal, location-based social network features outperform online social network features if we try to predict interactions between users. However, if we try to predict whether or not this communication was also reciprocal, we find that online social network features seem to be superior.Keywordsonline social networkslocation-based social networkslink prediction problempredicting interactionspredicting reciprocityvirtual worldsSecond Life

In recent years, due to the booming development of online social networks, fake news for various commercial and political purposes has been appearing in large numbers and widespread in the online world. With deceptive words, online social network users can get infected by these online fake news easily, which has brought about tremendous effects on the offline society already. An important goal in improving the trustworthiness of information in online social networks is to identify the fake news timely. This paper aims at investigating the principles, methodologies and algorithms for detecting fake news articles, creators and subjects from online social networks and evaluating the corresponding performance. This paper addresses the challenges introduced by the unknown characteristics of fake news and diverse connections among news articles, creators and subjects. This paper introduces a novel automatic fake news credibility inference model, namely FakeDetector. Based on a set of explicit and latent features extracted from the textual information, FakeDetector builds a deep diffusive network model to learn the representations of news articles, creators and subjects simultaneously. Extensive experiments have been done on a real-world fake news dataset to compare FakeDetector with several state-of-the-art models, and the experimental results have demonstrated the effectiveness of the proposed model.

In recent years, due to the booming development of online social networks, fake news for various commercial and political purposes has been appearing in large numbers and widespread in the online world. With deceptive words, online social network users can get infected by these online fake news easily, which has brought about tremendous effects on the offline society already. An important goal in improving the trustworthiness of information in online social networks is to identify the fake news timely. This paper aims at investigating the principles, methodologies and algorithms for detecting fake news articles, creators and subjects from online social networks and evaluating the corresponding performance. This paper addresses the challenges introduced by the unknown characteristics of fake news and diverse connections among news articles, creators and subjects. This paper introduces a novel gated graph neural network, namely FAKEDETECTOR. Based on a set of explicit and latent features extracted from the textual information, FAKEDETECTOR builds a deep diffusive network model to learn the representations of news articles, creators and subjects simultaneously. Extensive experiments have been done on a real-world fake news dataset to compare FAKEDETECTOR with several state-of-the-art models, and the experimental results are provided in the full-version of this paper at [13].

Online social media plays an important role during real world events such as natural calamities, elections, social movements etc. Since the social media usage has increased, fake news has grown. The social media is often used by modifying true news or creating fake news to spread misinformation. The creation and distribution of fake news poses major threats in several respects from a national security point of view. Hence Fake news identification becomes an essential goal for enhancing the trustworthiness of the information shared on online social network. Over the period of time many researcher has used different methods, algorithms, tools and techniques to identify fake news content from online social networks. The aim of this paper is to review and examine these methodologies, different tools, browser extensions and analyze the degree of output in question. In addition, this paper discuss the general approach of fake news detection as well as taxonomy of feature extraction which plays an important role to achieve maximum accuracy with the help of different Machine Learning and Natural Language Processing algorithms.

Fake news detection has become a pressing issue due to the rapid propagation of misinformation through various online platforms. In recent years, due to the booming development of online social networks, fake news for various commercial and political purposes has been appearing in large numbers and widespread in the online world. An important goal in improving the trustworthiness of information in online social networks is to identify the fake news timely. This paper aims at investigating the principles, methodologies and algorithms for detecting fake news articles, creators and subjects from online social networks and evaluating the corresponding performance. Information carefulness on Internet, especially on social media, is an increasingly important concern, but web-scale data hampers, ability to identify, evaluate and correct such data, or so called "fake news," present in these platforms. In this paper, we propose a method for "fake news" detection and ways to apply it on Facebook, one of the most popular online social media platforms. This method uses Naive Bayes classification model to predict whether a post on Facebook will be labelled as real or fake.

ABSTRACTDue to the popularity and user friendliness of the Internet, numbers of users of online social networks (OSNs) and social media have grown significantly. However, globally utilised, social networks are the consequence of the lack of understanding of secrecy and protection on OSN and media has increased. Secrecy and surety of OSNs need to be inquired from various positions. According to recent studies, OSN users expose their private information such as email address, phone number etc. In this paper, we have presented a high-level classification of recent OSN attacks for recognising the problem and analysing the blow of such attacks on World Wide Web. We have also discussed OSN attacks on different social networking web applications by citing certain recent reports such as Kaspersky security network and Sophos security threat report. We also offer some simple-to-implement user practice tips to protect the system and user’s information. In addition to this, we have discussed a comprehensive analysis of numerous defensive approaches on OSN security. Lastly, based on the acknowledged strength and faults of these defensive approaches, we have explained open research issues.