scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Fake News Detection on Social Media: A Data Mining Perspective

01 Sep 2017-Sigkdd Explorations (ACM)-Vol. 19, Iss: 1, pp 22-36
TL;DR: Wang et al. as discussed by the authors presented a comprehensive review of detecting fake news on social media, including fake news characterizations on psychology and social theories, existing algorithms from a data mining perspective, evaluation metrics and representative datasets.
Abstract: Social media for news consumption is a double-edged sword. On the one hand, its low cost, easy access, and rapid dissemination of information lead people to seek out and consume news from social media. On the other hand, it enables the wide spread of \fake news", i.e., low quality news with intentionally false information. The extensive spread of fake news has the potential for extremely negative impacts on individuals and society. Therefore, fake news detection on social media has recently become an emerging research that is attracting tremendous attention. Fake news detection on social media presents unique characteristics and challenges that make existing detection algorithms from traditional news media ine ective or not applicable. First, fake news is intentionally written to mislead readers to believe false information, which makes it difficult and nontrivial to detect based on news content; therefore, we need to include auxiliary information, such as user social engagements on social media, to help make a determination. Second, exploiting this auxiliary information is challenging in and of itself as users' social engagements with fake news produce data that is big, incomplete, unstructured, and noisy. Because the issue of fake news detection on social media is both challenging and relevant, we conducted this survey to further facilitate research on the problem. In this survey, we present a comprehensive review of detecting fake news on social media, including fake news characterizations on psychology and social theories, existing algorithms from a data mining perspective, evaluation metrics and representative datasets. We also discuss related research areas, open problems, and future research directions for fake news detection on social media.
Citations
More filters
Journal ArticleDOI
TL;DR: In this article , an automated system called DSS was proposed for early detection of fake news by leveraging the propagation tree and the stance network simultaneously and dynamically, and the outputs of these components were aggregated to determine the veracity of the news articles.
Abstract: Nowadays, online social media play a significant role in news broadcasts due to their convenience, speed, and accessibility. Social media platforms leverage the rapid production of a large volume of information and cause the propagation of untrustworthy and fake news. Since fake news is engineered to deceive a wide range of readers deliberately, it is not easy to detect them merely based on the news content. Hence, more information, such as the social context, is needed. Moreover, to limit the impact of fake news on society, it is essential to detect them as early as possible. In this paper, we have developed an automated system “DSS” for the early detection of fake news wherein we leverage the propagation tree and the stance network simultaneously and dynamically. Our proposed model comprises three major components: Dynamic analysis, Static analysis, and Structural analysis. During dynamic analysis, a recurrent neural network is used to encode the evolution pattern of the propagation tree and the stance network over time. The static analysis uses a fully connected network to precisely represent the overall characteristics of the propagation tree and the stance network at the end of a detection deadline. The node2vec algorithm is used during structural analysis as a graph embedding model to encode the structure of the propagation tree and the stance network. Finally, the outputs of these components are aggregated to determine the veracity of the news articles. Our proposed model is evaluated on the FakeNewsNet repository, comprising two recent well-known datasets in the field, namely PolitiFact and GossipCop. Our results show encouraging performance, outperforming the state-of-the-art methods by 8.2% on the PolitiFact and 3% on the GossipCop datasets. Early detection of fake news is the merit of the proposed model. The DSS model provides outstanding accuracy in the early stages of spreading, as well as the later stages.

31 citations

Journal ArticleDOI
01 Apr 2020
TL;DR: A deep learning framework for clickbait detection is presented and it is believed that the framework’s architecture has played a pivotal role to outperform the current state of the art with a classification accuracy of 97%.
Abstract: Social networks are generating huge amounts of complex textual data which is becoming increasingly difficult to process intelligently. Misinformation on social media networks, in the form of fake news, has the power to influence people, sway opinions and even have a decisive impact on elections. To shield ourselves against manipulative misinformation, we need to develop a reliable mechanism to detect fake news. Yellow journalism along with sensationalism has done a lot of damage by misrepresenting facts and manipulating readers into believing false narratives through hyperbole. Clickbait does exactly this by using characteristics of natural language to entice users into clicking a link and can hence be classified as fake news. In this paper, we present a deep learning framework for clickbait detection. The framework is trained to model the intrinsic characteristics of clickbait for knowledge discovery and then used for decision making by classifying headlines as either clickbait or legitimate news. We focus our attention on the linguistic analysis during the knowledge discovery phase as we investigate the underlying structure of clickbait headlines using our Part of Speech Analysis Module. The decision-making task of classification is carried out using long short-term memory. We believe that it is our framework’s architecture that has played a pivotal role to outperform the current state of the art with a classification accuracy of 97%.

30 citations

Journal ArticleDOI
TL;DR: A dynamic blocking period (DBP) approach as a solution for the MRIM problem and a new formulation of an individual’s opinion toward a rumor based on a Markov chain representation, which adds a layer of realism to the proposed model.
Abstract: The malicious rumors have tremendously attracted a more substantial number of researchers to join the fight against the propagation of these types of information in online social networks (OSNs). The spread of rumors has a severe impact on society, which can creates political conflicts, shape public opinion and weakens their trust in governments; therefore, it must be stopped as soon as it is detected. This paper investigates the problem of minimizing the influence of malicious rumors that emerge during breaking news, which are characterized by the dissemination of a large number of malicious information over a short period. Therefore, we introduce the problem of multi-rumors influence minimization (MRIM) in OSNs and propose a solution to it. To this end, we design a multi-rumor propagation model named the HISBMmodel that captures the propagation process of multi-rumors in OSNs. Moreover, we present a new formulation of an individual’s opinion toward a rumor based on a Markov chain representation, which adds a layer of realism to the proposed model. Subsequently, we propose a dynamic blocking period (DBP) approach as a solution for the MRIM problem. The main objective is to minimize both the spread and the influence of these rumors in OSNs. The proposed method selects and blocks nodes that most likely to spread a large number of rumors and support them. Different from existing methods, the proposed solution does not block nodes for an unlimited period, but this period is estimated according to the high activity of a node in an OSN. The survival theory has been exploited in this work to provide a solution formulated from the perspective of probabilistic inference of networks. Consequently, an algorithm has been proposed based on a likelihood principle to select the target nodes, which guarantees a ( 1 − 1 ∕ e ) -approximation of the optimal solution. The experimental results show that the HISBMmodel could capture the propagation of multi-rumor propagation more accurately than classical models and provides metrics to assess the impact of rumors efficiently. Moreover, the results show the outstanding performance of the proposed approach compared to the other solution in the literature. The experimental results show that in the worst-case, the DBP achieves on an average 37.66% reduction on the impact of rumors, compared to 18.46% obtained by the second-best method. However, in the best-case the performance of the proposed method reached 93.38% where second-best method achieved only 57.65% on an average. Besides, even though when the number of rumors is high, the DBP could achieve on an average 68.01% reduction on the impact of rumors.

30 citations

Journal ArticleDOI
21 Feb 2020-PLOS ONE
TL;DR: News comment toxicity can be characterized as topic-drivenoxicity that targets topics rather than as vindictive toxicity that targets users or groups, and practical implications suggest that humanistic framing of the news story can reduce toxicity in the comments of an otherwise toxic topic.
Abstract: Hateful commenting, also known as ‘toxicity’, frequently takes place within news stories in social media. Yet, the relationship between toxicity and news topics is poorly understood. To analyze how news topics relate to the toxicity of user comments, we classify topics of 63,886 online news videos of a large news channel using a neural network and topical tags used by journalists to label content. We score 320,246 user comments from those videos for toxicity and compare how the average toxicity of comments varies by topic. Findings show that topics like Racism, Israel-Palestine, and War & Conflict have more toxicity in the comments, and topics such as Science & Technology, Environment & Weather, and Arts & Culture have less toxic commenting. Qualitative analysis reveals five themes: Graphic videos, Humanistic stories, History and historical facts, Media as a manipulator, and Religion. We also observe cases where a typically more toxic topic becomes non-toxic and where a typically less toxic topic becomes “toxicified” when it involves sensitive elements, such as politics and religion. Findings suggest that news comment toxicity can be characterized as topic-driven toxicity that targets topics rather than as vindictive toxicity that targets users or groups. Practical implications suggest that humanistic framing of the news story (i.e., reporting stories through real everyday people) can reduce toxicity in the comments of an otherwise toxic topic.

30 citations

Posted Content
TL;DR: In this article, the authors present a comprehensive survey on the recent advances in terms of detection, characterization and mitigation of false news that propagate on social media, as well as the challenges and the open questions that await future research on the field.
Abstract: In the past few years, the research community has dedicated growing interest to the issue of false news circulating on social networks. The widespread attention on detecting and characterizing false news has been motivated by considerable backlashes of this threat against the real world. As a matter of fact, social media platforms exhibit peculiar characteristics, with respect to traditional news outlets, which have been particularly favorable to the proliferation of deceptive information. They also present unique challenges for all kind of potential interventions on the subject. As this issue becomes of global concern, it is also gaining more attention in academia. The aim of this survey is to offer a comprehensive study on the recent advances in terms of detection, characterization and mitigation of false news that propagate on social media, as well as the challenges and the open questions that await future research on the field. We use a data-driven approach, focusing on a classification of the features that are used in each study to characterize false information and on the datasets used for instructing classification methods. At the end of the survey, we highlight emerging approaches that look most promising for addressing false news.

30 citations

References
More filters
Journal ArticleDOI
28 May 2015-Nature
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Abstract: Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

46,982 citations

Book ChapterDOI
TL;DR: In this paper, the authors present a critique of expected utility theory as a descriptive model of decision making under risk, and develop an alternative model, called prospect theory, in which value is assigned to gains and losses rather than to final assets and in which probabilities are replaced by decision weights.
Abstract: This paper presents a critique of expected utility theory as a descriptive model of decision making under risk, and develops an alternative model, called prospect theory. Choices among risky prospects exhibit several pervasive effects that are inconsistent with the basic tenets of utility theory. In particular, people underweight outcomes that are merely probable in comparison with outcomes that are obtained with certainty. This tendency, called the certainty effect, contributes to risk aversion in choices involving sure gains and to risk seeking in choices involving sure losses. In addition, people generally discard components that are shared by all prospects under consideration. This tendency, called the isolation effect, leads to inconsistent preferences when the same choice is presented in different forms. An alternative theory of choice is developed, in which value is assigned to gains and losses rather than to final assets and in which probabilities are replaced by decision weights. The value function is normally concave for gains, commonly convex for losses, and is generally steeper for losses than for gains. Decision weights are generally lower than the corresponding probabilities, except in the range of low prob- abilities. Overweighting of low probabilities may contribute to the attractiveness of both insurance and gambling. EXPECTED UTILITY THEORY has dominated the analysis of decision making under risk. It has been generally accepted as a normative model of rational choice (24), and widely applied as a descriptive model of economic behavior, e.g. (15, 4). Thus, it is assumed that all reasonable people would wish to obey the axioms of the theory (47, 36), and that most people actually do, most of the time. The present paper describes several classes of choice problems in which preferences systematically violate the axioms of expected utility theory. In the light of these observations we argue that utility theory, as it is commonly interpreted and applied, is not an adequate descriptive model and we propose an alternative account of choice under risk. 2. CRITIQUE

35,067 citations

Book ChapterDOI
09 Jan 2004
TL;DR: A theory of intergroup conflict and some preliminary data relating to the theory is presented in this article. But the analysis is limited to the case where the salient dimensions of the intergroup differentiation are those involving scarce resources.
Abstract: This chapter presents an outline of a theory of intergroup conflict and some preliminary data relating to the theory. Much of the work on the social psychology of intergroup relations has focused on patterns of individual prejudices and discrimination and on the motivational sequences of interpersonal interaction. The intensity of explicit intergroup conflicts of interests is closely related in human cultures to the degree of opprobrium attached to the notion of "renegade" or "traitor." The basic and highly reliable finding is that the trivial, ad hoc intergroup categorization leads to in-group favoritism and discrimination against the out-group. Many orthodox definitions of "social groups" are unduly restrictive when applied to the context of intergroup relations. The equation of social competition and intergroup conflict rests on the assumptions concerning an "ideal type" of social stratification in which the salient dimensions of intergroup differentiation are those involving scarce resources.

14,812 citations

Journal ArticleDOI
TL;DR: Cumulative prospect theory as discussed by the authors applies to uncertain as well as to risky prospects with any number of outcomes, and it allows different weighting functions for gains and for losses, and two principles, diminishing sensitivity and loss aversion, are invoked to explain the characteristic curvature of the value function and the weighting function.
Abstract: We develop a new version of prospect theory that employs cumulative rather than separable decision weights and extends the theory in several respects. This version, called cumulative prospect theory, applies to uncertain as well as to risky prospects with any number of outcomes, and it allows different weighting functions for gains and for losses. Two principles, diminishing sensitivity and loss aversion, are invoked to explain the characteristic curvature of the value function and the weighting functions. A review of the experimental evidence and the results of a new experiment confirm a distinctive fourfold pattern of risk attitudes: risk aversion for gains and risk seeking for losses of high probability; risk seeking for gains and risk aversion for losses of low probability. Expected utility theory reigned for several decades as the dominant normative and descriptive model of decision making under uncertainty, but it has come under serious question in recent years. There is now general agreement that the theory does not provide an adequate description of individual choice: a substantial body of evidence shows that decision makers systematically violate its basic tenets. Many alternative models have been proposed in response to this empirical challenge (for reviews, see Camerer, 1989; Fishburn, 1988; Machina, 1987). Some time ago we presented a model of choice, called prospect theory, which explained the major violations of expected utility theory in choices between risky prospects with a small number of outcomes (Kahneman and Tversky, 1979; Tversky and Kahneman, 1986). The key elements of this theory are 1) a value function that is concave for gains, convex for losses, and steeper for losses than for gains,

13,433 citations

Trending Questions (1)
Issue of fake news

The paper discusses the issue of fake news on social media and its potential negative impacts on individuals and society.