True News Research Articles

Automatic Fake News Detection for Romanian Online News

This paper proposes a supervised machine learning system to detect fake news in online sources published in Romanian. Additionally, this work presents a comparison of the obtained results by using recurrent neural networks based on long short-term memory and gated recurrent unit cells, a convolutional neural network, and a Bidirectional Encoder Representations from Transformers (BERT) model, namely RoBERT, a pre-trained Romanian BERT model. The deep learning architectures are compared with the results achieved by two classical classification algorithms: Naïve Bayes and Support Vector Machine. The proposed approach is based on a Romanian news corpus containing 25,841 true news items and 13,064 fake news items. The best result is over 98.20%, achieved by the convolutional neural network, which outperforms the standard classification methods and the BERT models. Moreover, based on irony detection and sentiment analysis systems, additional details are revealed about the irony phenomenon and sentiment analysis field which are used to tackle fake news challenges.

An Ensemble Machine Learning Approach for Fake News Detection and Classification Using a Soft Voting Classifier

Fake news has grown in popularity and spread as a result of increased insecurity, political events, and pandemics, among other things. This study used an ensemble machine learning technique to better predict fake news on social media based on the content of news articles. The proposed model used a soft voting classifier to aggregate four machine learning algorithms, namely, Naïve Bayes, Support Vector Machine (SVM), and Logistic Regression, for the classification of news articles as fake or real. GridSearchCV was used to fine-tune the algorithms to get the optimal results during the training process. A Kaggle dataset was used for the experiment; it was comprised of both false and true news. Performance evaluation metrics were used to measure the performance of the base learners and our proposed ensemble technique on the dataset. The results of our experiment show that the proposed ensemble approach produced the highest accuracy, precision, recall, and F1_score values of 93%, 94%, 92%, and 93%, respectively, on the dataset as compared to the individual learners. This approach may also be used in other classification techniques for spam detection, sentiment analysis, and prediction of loan eligibility, among other things.

Fake news on Social Media: the Impact on Society

Fake news (FN) on social media (SM) rose to prominence in 2016 during the United States of America presidential election, leading people to question science, true news (TN), and societal norms. FN is increasingly affecting societal values, changing opinions on critical issues and topics as well as redefining facts, truths, and beliefs. To understand the degree to which FN has changed society and the meaning of FN, this study proposes a novel conceptual framework derived from the literature on FN, SM, and societal acceptance theory. The conceptual framework is developed into a meta-framework that analyzes survey data from 356 respondents. This study explored fuzzy set-theoretic comparative analysis; the outcomes of this research suggest that societies are split on differentiating TN from FN. The results also show splits in societal values. Overall, this study provides a new perspective on how FN on SM is disintegrating societies and replacing TN with FN.

HOAX DI ERA DIGITAL: SOLUSI AL-QUR’AN DALAM MENYIKAPI BERITA HOAX

Hoax is fake news that is deliberately made as if it is true news. Fake news or spread like a virus. This research is motivated by the rapid development of knowledge of technology and information, everything can be obtained quickly and instantly, as well as communication information. In the social environment, information also has an impact on the information currently circulating, especially on social media. The information circulating on social media is not known for certain. The circulation of hoax news is easy, especially in people whose literacy levels are still very low. Usually, they easily accept information for granted without checking. They disseminate it without considering the accuracy of the information it receives. The public finally fell into the confusion of news, provocation and mutual suspicion. Facing these problems, it is important to look back at the perspective of the Qur'an on the phenomenon of spreading false news. This study is important, because it is related to the position of the Qur'an which is believed to be a way of life for Muslims in Indonesia. Therefore, it is important to explore the response of the Qur'an, especially QS. An-Nur: 11 on actual phenomena such as hoaxes. So that as selective and critical Muslims we can find the best solution according to the Qur'an when dealing with various hoax news that are already rampant today.

Evidence-Aware Multilingual Fake News Detection

Due to the rapid growth of the Internet and the subsequent rise of social media users, sharing information has become more flexible than ever before. This unrestricted freedom has also led to an increase in fake news. During the Covid-19 outbreak, fake news spread globally, negatively affecting authorities’ decisions and the health of individuals. As a result, governments, media agencies, and academics have established fact-checking units and developed automatic detection systems. Research approaches focused largely on writing styles, propagation patterns, and building knowledge bases that serve as a reference for fact checking. However, little work has been done to assess the credibility of the source of the claim to be checked. This paper proposes a general framework for detecting fake news that uses external evidence to verify the veracity of online news in a multilingual setting. Search results from Google are used as evidence, and the claim is cross-checked with the top five search results. Additionally, we associate a vector of credibility scores with each evidence source based on the domain name and website reputation metrics. All of these components are combined to derive better predictions of the veracity of claims. Further, we analyze the claim-evidence entailment relationship and select supporting and refuting evidence to cross-check with the claim. The selection free approach yields better detection performance. In this work, we consider as a case study Covid-19 related news. Our framework achieves an F1-score of 0.85 and 0.97 in distinguishing fake from true news on XFact and Constraint datasets respectively. With the achieved results, the proposed framework present a promising automatic fact checker for both early and late detection.

Artificial Intelligence and the Future of News

The emergence of Artificial Intelligence (AI) is a direct result of our need for social progress. However, the speed at which it penetrates all domains of our lives influences how we understand the world, communicate, travel, and work. This paper aims to analyze the phenomenon of fake news as a direct consequence of AI making its way into the world of journalism as well as the redefinition of journalism caused by implementing AI in the work environment. Gradually, the development of new technologies created the conditions for a new kind of freedom, allowing individuals to express themselves throughout a constantly increasing number of platforms. In addition, digitization also affects the work of journalists, leading to the following questions: Is the freedom granted by new technologies beneficial or toxic? How can we distinguish between true and fake news? What is the future of journalism? Will algorithms be able to create better content than humans?

The fake news graph analyzer: An open-source software for characterizing spreaders in large diffusion graphs

<h2>Abstract</h2> In the study of fake news spreading, it is essential to know how different types of spreaders differ in terms of their characteristics, interconnections, and cascading flow. The fake news graph analyzer (FNGA) is an open-source software that provides the required computations for such extended analyses on large graphs. Moreover, FNGA generates data for graph visualizations. Also, FNGA is designed to consider the spreading of both fake and true news simultaneously in the graph, leading to a variety of confrontational patterns. FNGA facilitates future research on fake news and the diffusion of any contagion within a graph of entities.

AdaBoost Ensemble Learning on top of Naive Bayes Algorithm to Discriminate Fake and Genuine News from Social Media

There is a continuous increase in social media usage and a huge interaction takes place between users. In this context, fake news circulation or flood becomes a real thread for social media users from various perspectives. Fake news is defined as presentation of misleading information as true news. In this view, fake news is fabricated news that aims to manipulate public opinion to obtain a benefit. For example, increasing readership for profiting through clickbaits is such an aim. Social media users are manipulated through attention grabbing headlines or web-links to increase number of visitors. Therefore, an automated fake news identification model can be used by social media users to filter inadvertent web-traffic. For this goal machine learning algorithms are used in the literature as a solution for fake news problem. In machine learning literature, advancing performance of the base models is crucial. Ensemble learning is one of the key solutions to enhance model efficiency. In this work, we first generated a set of baseline machine learning algorithms and we tested them in terms of their fake news identification ability. We then made use of ensemble learning strategy to further enhance obtained results. More precisely, we obtained Naïve Bayes Multinomial classifier as the best fake news predictor having 96.74 % accuracy. We then further improved this prediction ability to 98.2 % by applying an AdaBoost ensemble learning strategy.

The Effects of Two Association Measures on L2 Collocation Processing

The influence of association measures has been little examined in research on L2 collocation processing. For this reason, the present study replicated &amp;Ouml;ks&amp;uuml;z et al. (2020) experiment on intermediate L2 learners of English to determine whether the association measure mutual information (MI) is a stronger predictor of L2 performance than the Log Dice measure. Twenty-two intermediate Arab learners of English completed a timed acceptability judgment task on the online Gorilla platform. The task included (1) high-frequent collocations (e.g., bad news), (2) low-frequent collocations (e.g., only friend), and (3) non-collocates (e.g., true news, wrong friend) which had differing MI and Log Dice scores. Mixed-effects models were built to analyze the participants&amp;rsquo; reaction times to the three conditions. The results showed that the frequency of the collocation (operationalized as item type) and its length significantly influenced reaction times, while both MI and Log Dice scores did not surface as significant predictors. This suggests that intermediate English L2 learners are not sensitive to corpus-based association measures. The results have important implications for L2 teaching and testing and may indicate that it is not worthwhile to determine which collocations to include in the materials based mainly on the strength of the association.

“If This account is True, It is Most Enormously Wonderful”: Interestingness-If-True and the Sharing of True and False News

Why would people share news they think might not be accurate? We identify a factor that, alongside accuracy, drives the sharing of true and fake news: the ‘interestingness-if-true’ of a piece of news. In three pre-registered experiments (N = 904), participants were presented with a series of true and fake news, and asked to rate the accuracy of the news, how interesting the news would be if it were true, and how likely they would be to share it. Participants were more willing to share news they found more interesting-if-true, as well as news they deemed more accurate. They deemed fake news less accurate but more interesting-if-true than true news, and were more likely to share true news than fake news. As expected, interestingness-if-true differed from interestingness and accuracy, and had good face validity. Higher trust in mass media was associated with a greater ability to discern true from fake news, and participants rated as more accurate news that they had already been exposed to (especially for true news). We argue that people may not share news of questionable accuracy by mistake, but instead because the news has qualities that compensate for its potential inaccuracy, such as being interesting-if-true.

Higher Classification of Fake Political News Using Decision Tree Algorithm Over Naive Bayes Algorithm

Aim: The main aim of the study proposed is to perform higher classification of fake political news by implementing fake news detectors using machine learning classifiers by comparing their performance. Materials and Methods: By considering two groups such as Decision Tree algorithm and Naive Bayes algorithm. The algorithms have been implemented and tested over a dataset which consists of 44,000 records. Through the programming experiment which is performed using N=10 iterations on each algorithm to identify various scales of fake news and true news classification. Result: After performing the experiment the mean accuracy of 99.6990 by using Decision Tree algorithm and the accuracy of 95.3870 by using Naive Bayes algorithm for fake political news in. There is a statistical significant difference in accuracy for two algorithms is p&lt;0.05 by performing independent samples t-tests. Conclusion: This paper is intended to implement the innovative fake news detection approach on recent Machine Learning Classifiers for prediction of fake political news. By testing the algorithms performance and accuracy on fake political news detection and other issues. The comparison results shows that the Decision Tree algorithm has better performance when compared to Naive Bayes algorithm.

Group chat analysis of hoax detection during the covid-19 pandemic using the k nearest neighbors algorithm and massive text processing

Group chat is the most widely used choice of various short information. Besides being easy to send messages, sharing short messages in group chat is considered effective compared to sending massively to several users. The ease of sending short messages in group chat is often used as the spread of fake news and untrue news or hoaxes, especially during the Covid-19 pandemic, the information shared can be easily shared by anyone without seeing a valid source. The dissemination of information related to Covid-19 without a clear source is a dangerous act, because it can lead users into false information and endanger themselves. Fake message detectors have not been widely implemented in instant message applications, for this reason, there is a need for a detector and a machine to analyze activities in group chat and see whether the message is included in content containing fake news or not. If a group chat has a lot of fake news, you can be sure that the group chat is not good to follow. The use of the K-Nearest Neighbors algorithm is considered quite effective in classifying an object, the results can be determined whether it is included in fake news, miss-information news, or true news. The process of processing messages is carried out by the massive text processing method because the characteristics of the text are different for each user so that text processing can be maximized for later classification. As a result, group chat can be analyzed based on active time, user messages, user activity, and messages sent between users.

Bias Gender dalam Surat Kabar (Analisis Isi Pemberitaan Harian Umum Nasional Waspada Sumatera Utara Edisi 01 Agustus-31 Agustus 2018)

This article discusses gender bias in the North Sumatra Waspada National Daily Newspaper, Edition 01 August-31 August 2018. The Waspada General Daily is one of the national newspapers in North Sumatra which still exists and is still active as a news channel. general daily. This newspaper has a vision and mission to deliver true news and does not favor one particular group. This article is a qualitative research with a descriptive approach. The results of the study indicate that the forms of gender bias that are displayed in the news by the General Waspada Daily are stereotypes, subordination, discrimination, and marginalization of women.

Network Inference from a Mixture of Diffusion Models for Fake News Mitigation

The dissemination of fake news intended to deceive people, influence public opinion and manipulate social outcomes, has become a pressing problem on social media. Moreover, information sharing on social media facilitates diffusion of viral information cascades. In this work, we focus on understanding and leveraging diffusion dynamics of false and legitimate contents in order to facilitate network interventions for fake news mitigation. We analyze real-world Twitter datasets comprising fake and true news cascades, to understand differences in diffusion dynamics and user behaviours with regards to fake and true contents. Based on the analysis, we model the diffusion as a mixture of Independent Cascade models (MIC) with parameters \theta_T , \theta_F over the social network graph; and derive unsupervised inference techniques for parameter estimation of the diffusion mixture model from observed, unlabeled cascades. Users influential in the propagation of true and fake contents are identified using the inferred diffusion dynamics. Characteristics of the identified influential users reveal positive correlation between influential users identified for fake news and their relative appearance in fake news cascades. Identified influential users tend to be related to topics of more viral information cascades than less viral ones; and identified fake news influential users have relatively fewer counts of direct followers, compared to the true news influential users. Intervention analysis on nodes and edges demonstrates capacity of the inferred diffusion dynamics in supporting network interventions for mitigation.

Mutual Influence of Users Credibility and News Spreading in Online Social Networks

A real-time news spreading is now available for everyone, especially thanks to Online Social Networks (OSNs) that easily endorse gate watching, so the collective intelligence and knowledge of dedicated communities are exploited to filter the news flow and to highlight and debate relevant topics. The main drawback is that the responsibility for judging the content and accuracy of information moves from editors and journalists to online information users, with the side effect of the potential growth of fake news. In such a scenario, trustworthiness about information providers cannot be overlooked anymore, rather it more and more helps in discerning real news from fakes. In this paper we evaluate how trustworthiness among OSN users influences the news spreading process. To this purpose, we consider the news spreading as a Susceptible-Infected-Recovered (SIR) process in OSN, adding the contribution credibility of users as a layer on top of OSN. Simulations with both fake and true news spreading on such a multiplex network show that the credibility improves the diffusion of real news while limiting the propagation of fakes. The proposed approach can also be extended to real social networks.

Dynamics of a Delayed Interactive Model Applied to Information Dissemination in Social Networks

Reducing fake news and rumor propagation through social media may be challenging to achieve when dealing with sensible contents and communities with free access to online shared resources. Controlling rumor dissemination and promoting true news are the main techniques used to strangle false information that may result in dramatic effect on human wellbeing in an open or closed environment. In this article, we studied a predator-prey model with constant delay in both predator and prey equations and applied the proposed model to the underlying relationship between the existing rumor propagating through social media and the related authoritative information containing the truth broadcast to reduce the respective rumor negative effect on the targeted community. We showed that the proposed system was very responsive to small perturbations and exhibited complex dynamical behavior around the steady-state equilibrium when interaction occurs and delay is applied, considering the controlled situations. Numerical results suggested applying relatively small delay, which represents the ideal time to publish the related propagating rumor curative content to reduce its diffusion speed and promote the truth.

The evaluation of fake and true news: on the role of intelligence, personality, interpersonal trust, ideological attitudes, and news consumption

Individual differences in cognitive abilities and personality help to understand individual differences in various human behaviors. Previous work investigated individual characteristics in light of believing (i.e., misclassifying) fake news. However, only little is known about the misclassification of true news as fake, although it appears equally important to correctly identify fake and true news for unbiased belief formation. An online study with N = 530 (n = 396 men) participants was conducted to investigate performance in a Fake and True News Test in association with i) performance in fluid and crystallized intelligence tests and the Big Five Inventory, and ii) news consumption as a mediating variable between individual characteristics and performance in the Fake and True News Test. Results showed that fluid intelligence was negatively correlated with believing fake news (the association did not remain significant in a regression model); crystallized intelligence was negatively linked to misclassifying true news. Extraversion was negatively and crystallized intelligence was positively associated with fake and true news discernment. The number of different news sources consumed correlated negatively with misclassifying true news and positively with fake and true news discernment. However, no meaningful mediation effect of news consumption was observed. Only interpersonal trust was negatively related to misclassifying both fake and true news as well as positively related to news discernment. The present findings reveal that underlying factors of believing fake news and misclassifying true news are mostly different. Strategies that might help to improve the abilities to identify both fake and true news based on the present findings are discussed.

Fake News on Social Media and Adolescent’s Cognition

This research aims to determine the extent to which teenagers distinguish true news from fake news and how these fake news affect adolescents’cognition. A lot of hoax information has sprung up on social media, especially during the 2019 Indonesian presidential election. The ability to check on the information spread in online media is influenced by each individual’s cognitive abilities. A person’s cognitive ability is to think rationally, including aspects of knowledge, understanding, application, analysis, synthesis, and evaluation. This study used an explanative survey method with a quantitative positivistic paradigm. The results showed that the most influencing X variable to the Y variable was the Satire variable, which is positive and unidirectional. The Hoax variable has the most influence on cognitive abilities, even though the value is negative and not unidirectional. This means, the lower the understanding of Hoax, the higher the level of cognitive abilities.

A Memory Network Information Retrieval Model for Identification of News Misinformation

The speed and volume at which misinformation spreads on social media have motivated efforts to automate fact-checking which begins with stance detection. For fake news stance detection, for example, many classification-based models have been proposed often with high complexity and hand-crafted features. Although these models can achieve high accuracy scores on a targeted small corpus of fake news, few are evaluated on a larger corpus of fake and conspiracy sites due to efficiency limitations and the lack of compatibility with the actual fact-checking process. In this article, we propose a practical two-stage stance detection model that is tailored to the real-life problem. Specifically, we integrate an information retrieval system with an end to end memory network model to sort articles based on their relevance to the claim and then identify the fine-grained stance of each relevant article towards its given claim. We evaluate our model on the Fake News Challenge dataset (FNC-1). The results show that the performance of our model is comparable to those of the state-of-the-art models, average weighted accuracy of 82.1, while it closely follows the real-life process of fact-checking. We also validate our model with a large dataset from a real-life fact-checking website (i.e., <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><uri>Snopes.com</uri></i> ), and the findings demonstrate the capability of the model in distinguishing false from true news headlines.

Exploring fake news identification using word and sentence embeddings

The widespread use of social media like Facebook, Twitter, Whatsapp, etc. has changed the way News is created and published; accessing news has become easy and inexpensive. However, the scale of usage and inability to moderate the content has made social media, a breeding ground for the circulation of fake news. Fake news is deliberately created either to increase the readership or disrupt the order in the society for political and commercial benefits. It is of paramount importance to identify and filter out fake news especially in democratic societies. Most existing methods for detecting fake news involve traditional supervised machine learning which has been quite ineffective. In this paper, we are analyzing word embedding features that can tell apart fake news from true news. We use the LIAR and ISOT data set. We churn out highly correlated news data from the entire data set by using cosine similarity and other such metrices, in order to distinguish their domains based on central topics. We then employ auto-encoders to detect and differentiate between true and fake news while also exploring their separability through network analysis.