Fake News Stories Research Articles

Modality deep-learning frameworks for fake news detection on social networks: a systematic literature review

Fake news on social networks is a challenging problem due to the rapid dissemination and volume of information, as well as the ease of creating and sharing content anonymously. Fake news stories are problematic not only for the credibility of online journalism, but also due to their detrimental real-world consequences. The primary research objective of this study is: What are the recent state-of-the-art modalities based on deep learning to detect fake news in social networks. This paper presents a systematic literature review of deep learning-based fake news detection models in social networks. The methodology followed a rigorous approach, including predefined criteria for study selection of deep learning modalities. This study focuses on the types of deep learning modalities; unimodal (refers to the use of a single model for analysis or modeling purposes) and multimodal models (refers to the integration of multiple models). The results of this review reveal the strengths and weaknesses of modalities approaches, as well as the limitations of low-resource languages datasets. Furthermore, it provides insights into future directions for deep learning models and different fact checking techniques. At the end of this study, we discuss the problem of fake news detection in the era of large language models in terms of advantages, drawbacks, and challenges.

Applying Evidential Pluralism to Justify Legal Responses to Online Fake News

Applying Evidential Pluralism to Justify Legal Responses to Online Fake News

Exploring the effects of location information on perceptions of news credibility and sharing intention

In recent years, the integration of location-based services into social media platforms has seen a significant surge, coinciding with the growing challenges posed by the proliferation of fake news online. However, the influence of location data on readers’ perceptions of online news credibility, particularly in relation to the reporters’ whereabouts, remains unclear. To investigate this relationship, we conducted a 3 (Topics: crime, science, health) × 2 (Location anchor: event-anchored or participant-anchored) × 4 (Proximity to location anchor - no, same, close-by or faraway location) mixed-method online study (N = 288) on Prolific. Our data collection involved presenting participants with news articles and assessing their credibility assessments and sharing intentions based on the proximity of those disseminating the news to both the subject matter of the news and the audience consuming it. Our findings reveal that the proximity of the reporter’s location to the readers’ location had a noticeable adverse impact on perceptions of news credibility and the likelihood of sharing it. Furthermore, we also identified a weak positive correlation between sharing intentions and trust in social media platforms. In addition, we observed that crime news were generally perceived as less credible compared to health and science news. Our research contributes significantly to a nuanced understanding of how location-based cues impact user behaviour when interacting with online news articles. Furthermore, it provides design insights for social media platforms aiming to enhance user trust and promote pro-social behaviours.

Toward an Efficient Hybrid Clustering and Classification Approach for Fake News Detection in Social Network

Objectives: The spread of fake news on social media has become a pressing issue in recent times. Despite various organizations' efforts to address this problem, it continues to persist, necessitating finding more effective solutions. This study implements a machine learning-based approach for identifying fake news on social media with improved accuracy. Methods : The study's methodology utilizes a combination of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) to extract semantic features from news articles. Then, a hybrid clustering and classification approach is used, which combines K-means clustering and Artificial Neural Network (ANN) classifiers. Data used is a secondary data consisting of 23481 world news articles obtained from the Reuters.com website and 21417 unreliable news from polifact.com. During the training process, the number of units and layers on the model was tuned to optimize model performance. The model was compared to other baseline models such as KNN, SVM, Decision tree, and Boosted decision tree to establish the best performing model. Findings: The results from the two algorithms were weighted to final classifications using Bayesian probability theory. The proposed approach achieved an accuracy of 99.78%, a sensitivity of 100%, and specificity equal to 99.73%. The model's precision is 99.74%, indicating its ability to identify fake news. The F-score of the approach is 99.87%, indicating that the model strikes a good balance between correctly classifying fake news articles and reliable news articles. The approach outperformed other machine learning classifiers, including KNN, SVM, Decision Tree, and Boosted Decision Tree. Novelty : The study applies a hybrid approach with a classification and clustering algorithm to improve detection of fake news on social media, the approach is tested with varied real-world datasets to establish its robustness under different vocabularies and vocabulary sizes. Keywords: Artificial Intelligence, Machine Learning, Deep Learning, Hybrid clustering approach, Classification, CNN, LSTM, Boosted Decision Tree, Social platforms, K-means

SIFG: an ensemble model for sieving fake news from genuine without metadata by combining syntactic and semantic features

ABSTRACT With the emergence of the Internet, social media, and smartphones, almost everyone can now claim that they have news in their pockets. This phenomenon makes people aware of their surroundings and knowledgeable of current events. But, it also presents new challenges, such as automatic detection, machine/bot-generated fake news, limited or no metadata, etc. In this paper, we mitigate some of these challenges by taking a step toward SIeving Fake News from Genuine (SIFG) and presenting a system named SIFG. In SIFG we have used basic and advanced Natural Language Processing techniques to detect online fake news automatically. This makes SIFG independent of the metadata, such as the source, network structure and behavior, temporal propagation, and responses, about the news. We also introduce specific Parts of Speech patterns, utilize Generalized Relevance Learning Vector Quantization for feature selection, and employ ensemble learning to improve the performance of SIFG. When tested with a publicly available online fake news dataset of 10,000 fake and 10,000 genuine news, SIFG shows promising results and achieves an accuracy in the range of 89.85% − 95%.

The strength of weak ties and fake news believability

Are we more likely to believe a social media news story shared by someone with whom we have a strong or weak tie? We tend to trust close ties more than weak ties, but weak ties are sources of new information more often than strong ones. We conducted an online experiment to examine the effect of tie strength (strong ties vs. weak ties) on the decision to believe or not believe fake news stories. Participants perceived false stories from weak ties to be more believable than false stories from strong ties (after controlling for the trustworthiness of the sharer). We found that a sharer's perceived ability to share reliable information plays a significant role in individuals' decision to believe news stories on social media, regardless of whether the source is a strong or weak tie. Interestingly, a sharer's perceived integrity was found to be important only when the information came from weak ties, while a sharer's perceived benevolence was not important for either weak or strong ties. These findings show that the perceived integrity of the sharer is a key factor in the decision to believe stories from weak ties, more so than from strong ties. Furthermore, a sharer's perceived ability to share reliable information is less critical when weak ties share true stories. The impact of weak ties does not stem from the novelty of their information, as we used identical headlines across both study groups. Thus, while the strength of weak ties effect is present in this context, the underlying theoretical mechanism differs from the novelty of information traditionally observed in other settings.

Fake News Detection: Traditional vs. Contemporary Machine Learning Approaches

Fake news is a growing problem in modern society. With the rise of social media and ever- increasing internet accessibility, news spreads like wildfire to millions of users in a very short time. The spread of fake news can have disastrous consequences, from decreased trust in news outlets to overturned elections. Such concerns call for automated tools to detect fake news articles. This study proposes a predictive model that can check the authenticity of a news article. The model is constructed using two different techniques to construct our model: (1) linguistic features and (2) feature extraction. We employed some widely used traditional (e.g. K-nearest neighbour (KNN) and support vector machine (SVM)) as well as state-of-the-art (e.g. bidirectional encoder representations from transformers (BERT) and extreme machine learning (ELM)) machine learning algorithms using feature extraction methods and linguistic features. After generating the models, performance metrics (e.g. accuracy and precision) are used to compare their performance. The model generated via logistic regression using feature hashing vectorisation emerged as the best model, with 99% accuracy. To the best of our knowledge, no extant studies have compared the traditional and contemporary methods in this context and demonstrated the traditional ones to be better performers. The fake news detection model can help curb the spread of fake news by acting as a tool for news organisations to check the authenticity of a news article.

Reasons to fight: preliminary results on motivations to combat fake news

Introduction. To encourage the public to combat online fake news and revalue truth, it is important to explore the factors that affect individual intention to combat fake news. Method. This study provides answers using survey data from a representative sample collected in the U.S. (N = 804). Analysis. We examined the impacts of planned-behaviour-theory components and prior experience of being deceived by fake news on the intentions of news verification, fake news refutation, and fact-checks sharing, with demographical characteristics, media use, and media credibility under control. The study also examined prior experience as a moderator in the models. Results. Results showed that subjective norms and prior experience of being deceived by fake news were positively correlated with intentions of all three behaviours that help to combat fake news. Prior experience moderated the effect of subjective norms on fake news refutation, and the effect of perceived control on fact-checks sharing. Conclusion. The findings of this study help scholars and industry practitioners to understand audiences’ interaction with online information and what drives audiences to combat information fakeness. Prior experience of being deceived by fake news is a significant driver.

AI Assisted Deceptive Content Analysis System Using Bi-LSTM

Abstract: In an age of widespread misinformation, creating accurate machine learning algorithms is vital for ensuring the integrity of information sharing. This project aims to develop a machine learning model capable of distinguishing between fake and true news articles. [1]The model utilizes a Bidirectional Long Short-Term Memory (Bi-LSTM) neural network architecture. Exploratory data analysis techniques are employed to gain in-sights into the characteristics and distributions within the dataset. Data visualization techniques aid in understanding patterns and relationships within the dataset. Additionally, unigram analysis is conducted to extract meaningful features from the text data. The datasets are then prepared for model training, involving preprocessing steps such as tokenization and vectorization. Fi-nally, the Bi-LSTM model is constructed, leveraging its ability to capture long-range dependencies in sequential data. The model is trained on the prepared datasets, optimized using appropri-ate techniques, and evaluated using metrics such as accuracy, precision, recall, and F1-score. The Bi-LSTM architecture offers the advantage of capturing long-range dependencies in sequential data, thereby enhancing the model’s ability to discern nuanced patterns in news articles. The primary objective of this project is to develop a robust and accurate system for automatically detecting fake news, thus playing a pivotal role in enhancing the dissemination of reliable information in the digital age.

Improvement of a Machine Learning Model Using a Sentiment Analysis Algorithm to Detect Fake News

These days, the problem of fake news has grown to be a major social and personal concern. With the amount of information generated through social media, it is very crucial to be able to detect and properly take care of that fake information. Previous studies proposed a machine learning model to detect fake news in online Thai health and medical articles. Still, the problem of detecting fake news with similar content but different objectives exists, and the accuracy of the model needs improvement. Therefore, this study aims to solve these problems by adding 33 new features, including textual features, sentiment-based features, and lexicon features, i.e., herbs, fruits, and vegetables, to identify the objective of an article. We trained and tested the model's prediction accuracy on a new dataset containing 582 reliable and 435 unreliable (fake news) articles from eight Thai websites. Our improved classification model using XGBoost with Lasso, the best feature selection method, achieved an accuracy of 97.76% without over-fitting, reflecting a 7.16% improvement over our earlier model.

Deceptive Content Detection Using Machine Learning

Deceptive content, such as fake news, poses a significant challenge in today's information landscape, influencing public opinion and decision-making processes. This paper presents an innovative approach for the detection of deceptive content using machine learning techniques. The proposed system leverages a combination of natural language processing and supervised learning algorithms to identify patterns indicative of misinformation in textual data Our approach leverages term frequency-inverse document frequency (TF-IDF) of bag-of-words and n-grams as feature extraction methods, complemented by the utilization of Support Vector Machine (SVM) as a classifier. Additionally, we introduce a meticulously curated dataset comprising both fake and genuine news articles to train and evaluate our proposed system. Our findings underscore the efficacy of the developed framework, demonstrating its capability in discerning between fake and authentic news articles. Keywords — Deceptive Content, TfidfVectorizer, Natural Language Processing, Text Classification, Passive-Aggressive Classifier, Machine Learning

Developing a Stressor Strain Outcome Model That Predicts Fake News Sharing Behaviour on Social Media: The Mediating Role of Social Media Exhaustion

Despite the growing corpus of knowledge on fake news sharing, nothing much is known about the relationship between the dissemination of fake news and social media exhaustion from an empirical standpoint. There is limited knowledge that exists to show if social media exhaustion could contribute to fake news-sharing behaviour. To address the gaps in the literature, this study created and evaluated a stressor strain outcome model that forecasts social media spread of fake news. It looked at the contributing elements of social media exhaustion before connecting it to disseminating fake news online. It also looked at how social media exhaustion functions as a mediator between its antecedents and fake news-sharing activity. Data was obtained from 1650 social media users using an online survey. Smart PLS structural equation modelling was used to examine the data. Our results, which drew on the stressor strain outcome model, demonstrated that, in the context of fake news-sharing behaviour, social media usage intensity is the most important predictor of social media exhaustion. Social media exhaustion was also predicted by information irrelevance, social media overload, the fear of missing out, and information overload. Also, social media tiredness predicts how people would share misleading news. Further research indicates that the link between information relevance, social overload, fear of missing out, information overload, and the dissemination of fake news is fully mediated by social media exhaustion. Conversely, it partially mediated the link between the frequency of using social media and the dissemination of false information. Our research provides recommendations to social media businesses and developers who wish to reduce concerns about social media tiredness and the spread of fake news.

Enriching the Fake News Process of Classifying Model using Deep Learning and Machine Learning Algorithm

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.

Deceptive Content Detection Using Machine Learning

Deceptive Content Detection Using Machine Learning

Fast Naïve Bayes classifiers for COVID-19 news in social networks

The growth of fake news has emerged as a substantial societal concern, particularly in the context of the COVID-19 pandemic. Fake news can lead to unwarranted panic, misinformed decisions, and a general state of confusion among the public. Existing methods to detect and filter out fake news have accuracy, speed, and data distribution limitations. This study explores a fast and reliable approach based on Naïve Bayes algorithms for fake news detection on COVID-19 news in social networks. The study used a dataset of 10,700 tweets and applied text pre-processing, term-weighting, document frequency thresholding (DFT), and synthetic minority oversampling techniques (SMOTE) to prepare the data for classification. The study assessed the performance and runtime of four models: gradient boosting (GDBT), decision tree (DT), multinomial Naïve Bayes (MNB), and complement Naïve Bayes (CNB). The testing results showed that the CNB model reaches the highest accuracy, precision, recall, and F1-score of approximately 92% each, with the shortest runtime of 0.55 seconds. This study highlights the potential of the CNB model as an effective tool for detecting online fake news about COVID-19, given its superior performance and rapid processing time.

Which Linguistic Cues Make People Fall for Fake News? A Comparison of Cognitive and Affective Processing

Fake news on social media has large, negative implications for society. However, little is known about what linguistic cues make people fall for fake news and, hence, how to design effective countermeasures for social media. In this study, we seek to understand which linguistic cues make people fall for fake news. Linguistic cues (e.g., adverbs, personal pronouns, positive emotion words, negative emotion words) are important characteristics of any text and also affect how people process real vs. fake news. Specifically, we compare the role of linguistic cues across both cognitive processing (related to careful thinking) and affective processing (related to unconscious automatic evaluations). To this end, we performed a within-subject experiment where we collected neurophysiological measurements of 42 subjects while these read a sample of 40 real and fake news articles. During our experiment, we measured cognitive processing through eye fixations, and affective processing in situ through heart rate variability. We find that users engage more in cognitive processing for longer fake news articles, while affective processing is more pronounced for fake news written in analytic words. To the best of our knowledge, this is the first work studying the role of linguistic cues in fake news processing. Altogether, our findings have important implications for designing online platforms that encourage users to engage in careful thinking and thus prevent them from falling for fake news.

Fake news detection in Dravidian languages using multiscale residual CNN_BiLSTM hybrid model

Fake news detection is the process of identifying news that contain purposeful misinformation disseminated through traditional news sources or social media platforms. Detecting fake news in Dravidian languages poses unique challenges due to the linguistic diversity and limited resources available for these languages. In this study, we propose a novel approach for fake news detection in Dravidian languages, leveraging contextualized word embeddings from MuRIL. MuRIL provides contextual embeddings that capture nuanced linguistic nuances, making it well-suited for the complexities of Dravidian languages. The proposed hybrid model combines multiscale residual CNN and BiLSTM layers to capture local and global dependencies in textual data effectively. The multiscale architecture allows the model to extract features at various levels of granularity while the BiLSTM layer captures long-range dependencies and contextual information. We performed extensive experiments on diverse datasets in Dravidian languages to evaluate the proposed approach. The results demonstrate the effectiveness of our hybrid model in discerning between genuine and fake news articles.

Who shares fake news on social media? Evidence from vaccines and infertility claims in sub-Saharan Africa.

The widespread dissemination of misinformation on social media is a serious threat to global health. To a large extent, it is still unclear who actually shares health-related misinformation deliberately and accidentally. We conducted a large-scale online survey among 5,307 Facebook users in six sub-Saharan African countries, in which we collected information on sharing of fake news and truth discernment. We estimate the magnitude and determinants of deliberate and accidental sharing of misinformation related to three vaccines (HPV, polio, and COVID-19). In an OLS framework we relate the actual sharing of fake news to several socioeconomic characteristics (age, gender, employment status, education), social media consumption, personality factors and vaccine-related characteristics while controlling for country and vaccine-specific effects. We first show that actual sharing rates of fake news articles are substantially higher than those reported from developed countries and that most of the sharing occurs accidentally. Second, we reveal that the determinants of deliberate vs. accidental sharing differ. While deliberate sharing is related to being older and risk-loving, accidental sharing is associated with being older, male, and high levels of trust in institutions. Lastly, we demonstrate that the determinants of sharing differ by the adopted measure (intentions vs. actual sharing) which underscores the limitations of commonly used intention-based measures to derive insights about actual fake news sharing behaviour.

Is Journalistic Truth Dead? Measuring How Informed Voters Are about Political News

To investigate general patterns in news information in the United States, we combine a protocol for identifying major political news stories, 11 monthly surveys with 15,000 participants, and a model of news discernment. When confronted with a true and a fake news story, 47 percent of subjects confidently choose the true story, 3 percent confidently choose the fake story, and the remaining half are uncertain. Socioeconomic differences are associated with large variations in the probability of selecting the true news story. Partisan congruence between an individual and a news story matters, but its impact is up to an order of magnitude smaller. (JEL D72, D83, L82)

The Detection of Fake Text News using a Dense-based 1D-CNN Deep Learning Algorithm

There are a lot of problems with fake news, which can make people think of things that ‎aren't true. Social media is one of the fastest ways to get information out there because it has ‎a big impact and can manipulate information in both good and bad ways. The goal of this ‎paper is the optimal use of deep learning algorithms to solve the problem of the paper. The research problem is how ‎accurately and to what extent can an individual distinguish between fake news articles using ‎natural language processing and classification algorithms. What are the steps that can be ‎taken to provide a solution?‎‎compared to the previous different methods to solve this problem, including some common ‎deep-learning methods. In this paper, we can find fake news can be found by using the term ‎inverse frequency document (TF-IDF) for feature extraction and a hybrid algorithm of One ‎Dimensional-Convolutional Neural Network (1D-CNN) and Dense as the classifier. The ‎experiments that the proposed dense-based 1D-CNN algorithm substantially outperforms ‎other up-to-date related algorithms with an accuracy of 100%.