Misinformation Research Articles

SOCIAL MEDIA FAKE ACCOUNT IDENTIFICATION USING ML

The proliferation of social media platforms has led to an increase in the creation of fake accounts. These accounts are used for various malicious activities, such as spreading false information, phishing, and identity theft. As a result, there is a growing need for effective methods to identify and eliminate fake accounts. This paper proposes a machine learning-based approach for social media fake account identification. This paper proposes a machine learning-based approach to identify fake accounts on social media platforms. Our method leverages a combination of feature extraction techniques and supervised learning algorithms to classify accounts as genuine or fake. We collect a large dataset of labeled social media accounts, including both genuine and fake profiles, and extract features from various sources such as profile information, network behavior, and content analysis. We experiment with multiple machine learning models, including Support vector machines(SVM),K-Nearest Neighbors Algorithm(KNN),Random forest, Logistic Regression & Artificial Neural Network(ANN) to evaluate their performance in identifying fake accounts. Our proposed method has significant implications for social media platform operators, policymakers, and researchers seeking to combat fake accounts and maintain online trust. The approach can be integrated with existing social media moderation tools to enhance the accuracy and efficiency of fake account identification. Key Words: Support vector machines(SVM),K-Nearest Neighbors Algorithm(KNN),Random forest, Logistic Regression & Artificial Neural Network(ANN),Python.

DENOTATIVE AND CONNOTATIVE MEANING IN VIRGIN VS. CHAD MEME IN KNOW YOUR MEME SITE

This research aims to find out how hidden meanings are conveyed in memes and the type of meme studied is a meme with the Virgin vs. Chad template and other similar template memes namely Swole Doge vs. Cheems on the official meme site and Know Your Meme's official Instagram account. By using descriptive qualitative methods, this research aims to analyze the meaning of denotation and connotation attached to several data. Researchers found 10 memes that use the template Virgin vs. Chad and 10 memes that use the Swole Doge vs. Cheems. The results of the analysis show that the denotational meaning in these memes shows figures that have been arranged and edited as creatively as possible by the creator without describing any further meaning, just figures and text written without context, while the connotative meaning in these memes describe the hidden meanings of the meme, such as how the meme template functions, the role of the figures displayed, and the written text has an implied meaning, whether it is the opinion of the meme maker, public opinion, facts in the field, even there are exaggerated opinions and even false information.

Conflict and Context: Jadidism, Pan-Islamism, and the Muslims of Akmolinsk at the Beginning of the 20th Century

Abstract This article analyzes a conflict between the imam of Akmolinsk’s Second Congregational Mosque Hujjat Mahmudov and the Tatar merchant Nur-Muhammad Zabirov. The conflict took place in 1912–1913, and attracted the attention of the public at large, editorial boards of Muslim newspapers, and the Russian colonial administration. The depictions of the conflict were contradictory and depended on who was telling the story: the immediate participants, residents of Akmolinsk, or external observers. When the imam accused the Tatar merchant of ignorance and a grossly over-extravagant lifestyle, the merchant’s defenders immediately accused the imam of spreading forbidden innovations and selling banned literature, i.e., the works by the Kazakh writer Mir-Zhaqïp Dulatov and the editor of the newspaper Waqït, Fatih Karimi. These works were regarded by imperial officials as politically dangerous on account of containing false information about the Romanov Dynasty, as well as Pan-Turkic and Pan-Islamic ideas. At first glance, the Akmolinsk story appears to illustrate how Muslims themselves made use of the imperial discourse about the threat of jadidism and Pan-Islamism to eliminate their enemies; but it also exhibits a series of distinct peculiarities. My aim is to show that it is not so much the conflict as such that is important, but rather the context in which it arose. A careful study of this context allows us to understand the principles by which the local society functioned. Focusing on specific representations of the conflict (newspaper accounts, the point of view of imperial bureaucrats, the petitions of the immediate participants), we ignore the epistemic value of other sources – for example, the opinions of local Muslims who do not necessarily describe what happened through the prism of fundamental contradictions and imply, among other things, the confrontation between so-called reformers and traditionalists. The Muslims of Akmolinsk, like those of other regions of the Russian Empire, were aware of the nature of external threats and challenges; however, they could also perceive them based on their own rationality as expressed in their prevailing cultural and everyday life. In some cases, that rationality was draped in pragmatism; in others, it stemmed from an attempt to protect cultural self-sufficiency – that is, a specific world of ideas and values; in yet others, it was justified by the need to carry out those small reforms and changes that could fit organically into the customary course of things.

A Narrative Review of the Digital Equity Gap of Apps for Cigarette Smoking Cessation for Persons Living in the Hispanosphere

Abstract Purpose of Review The Hispanosphere is a vast region of the world that has received little attention in the digital health literature. No study to date has examined the availability and quality of publicly available mobile applications (apps) for cigarette smoking cessation in this region. Three coders utilized the American Psychiatry Association (APA)’s Brief App Evaluation Model Screener (Brief-AEM Screener) to evaluate the quality of the label and public-facing screens of smoking cessation apps in Spanish. Availability of apps in the Hispanosphere was compared to availability of apps in the Anglosphere. Recent Findings We identified and reviewed 19 apps in Spanish in Google Play. The median score using the Brief-AEM Screener was 63 out of 100 suggesting generally acceptable app quality and features according to the quality standards for digital health tools proposed by the APA. However, we found (1) notable inaccurate and misleading labelling claims, (2) poor grammar or incomplete translations, and (3) a lack of cultural and linguistic adaptation to countries in the Hispanosphere. Our comparison of smoking cessation apps between the Hispanosphere and the Anglosphere suggested that there is a large digital equity gap between these two regions, with a four to sevenfold gap in app availability. Summary There is a relative shortage of quality and quantity of digital health apps for smoking cessation in the Hispanosphere. To ensure the cultural appropriateness of those digital interventions, it is essential that developers of digital health tools establish community partners in the region prior to developing apps for smoking cessation.

Evaluating ChatGPT's Role in Assessing Turkey's Medical Tourism Trends

Background and Aims: The primary objective of this study is to evaluate the performance of the ChatGPT as an expert in the field of medical tourism. Another objective of this study is to assess its evaluations regarding the current state and future prospects of medical tourism in Turkey from an artificial intelligence perspective. Methods: Within the scope of the study's objectives, questions were created for ChatGPT regarding the current state and future prospects of medical tourism in Turkey. First, the draft questions were prepared by the authors of this article using the literature. All questions were evaluated by experts through online interviews. Totally 8 experts have been evaluated the questionnaires. These experts consisted of two tourism professors who had research on medical tourism, three major medical tourism hospital managers, one reconstructive aesthetician clinic owner, and the Turkish Healthcare Travel Council Founding Chairman. The second step of the research questionnaire was applied to the ChatGPT Model 4, which was trained as a medical tourism expert. than test the answers of the AI used the tools “Completeness of content, Lack of false information in the content, Evidence supporting the content, Appropriateness of the content, and Relevance,” referred as CLEAR. All answers were evaluated by 41 experts who had articles and research on medical tourism in Turkey. To explain the methodology appropriately, reporting was conducted using the METRICS checklist, which was prepared for artificial intelligence studies. Results: TThe general answers of ChatGPT 4-o were accurate, informative, and helpful, providing a good overview of medical tourism in Turkey. However, the responses lacked detail, did not provide evidence-based information, and did not always address the nuances and cultural/social impacts of medical tourism. ChatGPT 4-o views the future of Turkey’s medical tourism as shiny and will force the lead in general. Conclusions: This study is important for revealing data on the current and future state of medical tourism through artificial intelligence. However, only a few studies have been conducted on artificial intelligence and medical tourism. To the best of our knowledge, there is no existing literature that systematically evaluates the ChatGPT responses of medical tourism experts. In this regard, it is believed that the study will benefit both academics and practitioners.

Ensemble based high performance deep learning models for fake news detection

Social media has emerged as a dominant platform where individuals freely share opinions and communicate globally. Its role in disseminating news worldwide is significant due to its easy accessibility. However, the increase in the use of these platforms presents severe risks for potentially misleading people. Our research aims to investigate different techniques within machine learning, deep learning, and ensemble learning frameworks in Arabic fake news detection. We integrated FastText word embeddings with various machine learning and deep learning methods. We then leveraged advanced transformer-based models, including BERT, XLNet, and RoBERTa, optimizing their performance through careful hyperparameter tuning. The research methodology involves utilizing two Arabic news article datasets, AFND and ARABICFAKETWEETS datasets, categorized into fake and real subsets and applying comprehensive preprocessing techniques to the text data. Four hybrid deep learning models are presented: CNN-LSTM, RNN-CNN, RNN-LSTM, and Bi-GRU-Bi-LSTM. The Bi-GRU-Bi-LSTM model demonstrated superior performance regarding the F1 score, accuracy, and loss metrics. The precision, recall, F1 score, and accuracy of the hybrid Bi-GRU-Bi-LSTM model on the AFND Dataset are 0.97, 0.97, 0.98, and 0.98, and on the ARABICFAKETWEETS dataset are 0.98, 0.98, 0.99, and 0.99 respectively. The study’s primary conclusion is that when spotting fake news in Arabic, the Bi-GRU-Bi-LSTM model outperforms other models by a significant margin. It significantly aids the global fight against false information by setting the stage for future research to expand fake news detection to multiple languages.

Quantum Cryptography and Blockchain-Based Social Media Platforms as a Dual Approach to Securing Financial Transactions in CBDCs and Combating Misinformation in U.S. Elections

This paper explores the integration of quantum cryptography and blockchain technology to address two pressing challenges: securing financial transactions in Central Bank Digital Currencies (CBDCs) and combating the spread of misinformation during U.S. elections through decentralized social media platforms. As quantum computing advances, traditional encryption methods may become obsolete, posing significant risks to digital financial systems. Quantum cryptography, with its quantum-resistant algorithms, offers enhanced protection for CBDC transactions, ensuring long-term security and privacy. Simultaneously, blockchain-based social media platforms provide a decentralized structure that can prevent the dissemination of false information by ensuring transparency and authenticity through cryptographic verification and consensus mechanisms. These platforms also facilitate decentralized identity management, empowering users to verify content without relying on centralized authorities. By combining quantum cryptography’s secure framework with blockchain’s decentralized transparency, this dual approach creates a more secure digital ecosystem that not only safeguards financial transactions but also strengthens democratic processes. The paper further addresses the regulatory and technical challenges associated with implementing these technologies and their potential to shape a more secure, transparent, and accountable future.

Sentiment analysis in infodemic management: leveraging the eppm Risk communication model

Infodemics are the rapid spread of false or misleading information related to public health emergencies, often through digital platforms. They can cause confusion, fear, and even harm to public health. This study investigates the application of sentiment analysis for infodemic management during disease outbreaks. Leveraging the Extended Parallel Process Model (EPPM) of risk communication, the research aims to categorize rumors based on their perceived threat level (high, medium, or low). Machine learning is employed to analyze infodemic text data collected from two Nigerian states (Oyo and Bauchi) to assess threat appraisal according to the EPPM model. The findings can inform targeted interventions for effective infodemic management before, during, and after outbreak of diseases.

An Accurate and Efficient Approach to Knowledge Extraction from Scientific Publications Using Structured Ontology Models, Graph Neural Networks, and Large Language Models

The rapid growth of biomedical literature makes it challenging for researchers to stay current. Integrating knowledge from various sources is crucial for studying complex biological systems. Traditional text-mining methods often have limited accuracy because they don’t capture semantic and contextual nuances. Deep-learning models can be computationally expensive and typically have low interpretability, though efforts in explainable AI aim to mitigate this. Furthermore, transformer-based models have a tendency to produce false or made-up information—a problem known as hallucination—which is especially prevalent in large language models (LLMs). This study proposes a hybrid approach combining text-mining techniques with graph neural networks (GNNs) and fine-tuned large language models (LLMs) to extend biomedical knowledge graphs and interpret predicted edges based on published literature. An LLM is used to validate predictions and provide explanations. Evaluated on a corpus of experimentally confirmed protein interactions, the approach achieved a Matthews correlation coefficient (MCC) of 0.772. Applied to insomnia, the approach identified 25 interactions between 32 human proteins absent in known knowledge bases, including regulatory interactions between MAOA and 5-HT2C, binding between ADAM22 and 14-3-3 proteins, which is implicated in neurological diseases, and a circadian regulatory loop involving RORB and NR1D1. The hybrid GNN-LLM method analyzes biomedical literature efficiency to uncover potential molecular interactions for complex disorders. It can accelerate therapeutic target discovery by focusing expert verification on the most relevant automatically extracted information.

Secure multi-synchronization of heterogeneous dynamical networks with deception attacks via event-triggered impulsive control

This article investigates the secure multi-synchronization control problem of the heterogeneous dynamical networks (DNs) subject to deception attacks (DAs). First of all, a heterogeneous DNs model under DAs is built. The deception attackers are assumed to inject false information into the sensor-to-controller channels and the controller-to-actuator channels. Then, the centralized and distributed event-triggered impulsive controllers (ETIC) are designed respectively for DNs subject to DAs to achieve secure multi-synchronization. The synchronization error converges to a bounded set dependent on the heterogeneity of networks and the total attack energy. In addition, the heterogeneous DNs without DAs under ETIC can achieve multi-synchronization. Finally, a numerical example is given to verify the correctness of the theoretical results.

Enhancing rumor detection with data augmentation and generative pre-trained transformer

The advent of social networks has facilitated the rapid dissemination of false information, including rumors, leading to significant societal and individual damages. Extensive research has been dedicated to rumor detection, ranging from machine learning techniques to neural networks. However, the existing methods could not learn the deep concepts of the rumor text to detect the rumor. In addition, imbalanced datasets in the rumor domain reduce the effectiveness of these algorithms. This study addresses this challenge by leveraging the Generative Pre-trained Transformer 2 (GPT-2) model to generate rumor-like texts, thus creating a balanced dataset. Subsequently, a novel approach for classifying rumor texts is proposed by modifying the GPT-2 model. We compare our results with state-of-art machine learning and deep learning methods as well as pre-trained models on the PHEME, Twitter15, and Twitter16 datasets. Our findings demonstrate that the proposed model, implementing advanced artificial intelligence techniques, has improved accuracy and F-measure in the application of detecting rumors compared to previous methods.

A graph mining-based approach to analyze the dynamics of the Twitter community of COVID-19 misinformation disseminators

This study explores the global problem of misinformation dissemination on social media, particularly Twitter, due to the COVID-19 pandemic. It identifies prominent disseminators, investigates the spread of false information and the ecosystem of disinformation spreaders, and assesses their online personalities. We track the interaction among fake news spreaders using the User-User Interaction Graph. The study reveals a rapidly growing population of disseminators, including professional spreaders, with over 3% dominating the others. The collaboration among fake news spreaders is high, highlighting the need for further research using publicly available online data to understand the community spreading malicious misinformation about COVID-19.

Fake News Detection Using Machine Learning

Abstract: The identification of fake news has grown in importance as false information circulates quickly via digital channels. The goal of this project is to combine deep learning and machine learning to create an automated system that can identify news stories as legitimate or fraudulent. The preprocessed text data in the dataset, which comprises of tagged news items, was done using methods such tokenization, stop word removal, and padding. A Convolutional Neural Network (Conv1D), which is based on deep learning, was combined with more conventional machine learning models, such as Naive Bayes, in a hybrid approach. After converting the text input into a series of tokens, semantic meanings were captured by using word embeddings. Important patterns from the word sequences were intended to be captured by the Conv1D model with global max pooling, whereas the Naive Bayes also used in the project.

Challenges and Techniques in Multilingual Fake News Detection

The spread of false information across language and cultural barriers poses a significant threat to global societies. This study investigates the obstacles in detecting misinformation in various languages, including linguistic diversity, limited datasets, cultural nuances, and the ever- changing strategies of disinformation propagators. These complex issues require advanced methods to effectively identify and combat false information across multiple languages. The research evaluates several prominent machine learning approaches, such as Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), Logistic Regression, Decision Trees, and Natural Language Processing (NLP) techniques. By examining their effectiveness in multilingual contexts, this study sheds light on the advantages and drawbacks of each method. It underscores the need for continuous innovation and collaborative efforts in developing robust detection systems that can adapt to the ever-changing landscape of misinformation. These initiatives aim to promote informed public discourse and improve information integrity across diverse cultural contexts. Key Words: Multilingual Fake News Detection, Machine Learning, Machine Learning algorithms, Natural Language Processing, Misinformation.

Evolutionary biology as a frontier for research on misinformation.

The field of misinformation studies has experienced a boom of scholarship in recent years. Buoyed by the emergence of information operations surrounding the 2016 election and the rise of so-called "fake news," researchers hailing from fields ranging from philosophy to computer science have taken up the challenge of detecting, analyzing, and theorizing false and misleading information online. In an attempt to understand the spread of misinformation online, researchers have adapted concepts from different disciplines. Concepts from epidemiology, for example, have opened doors to thinking about spread, contagion, and resistance. The life sciences offer concepts and theories to further extend what we know about how misinformation adapts; by viewing information as an organism within a complex ecosystem, we can better understand why some narratives succeed and others fail. Collaborations between misinformation researchers and life scientists to develop responsible adaptations of fitness models can bolster misinformation research.

Digital health literacy and health behaviour of schoolchildren: A representative study in Germany

Abstract Background Health information is increasingly available and plays a crucial role in making health decisions and developing healthy behaviours. Digital health literacy (DHL) enables one to distinguish between true and false health information online. Studies have found higher health literacy to be associated with healthier behaviour. However, there is no research on child DHL and health behaviour. This study aims to investigate the relationship between DHL and selected health behaviour of schoolchildren in Germany. Methods This cross-sectional study is based on a representative sample of (N = 1448) secondary schoolchildren (aged 9-18 years) in Germany across all 16 federal states and school forms. DHL was assessed using the child and adolescent version of the Digital Health Literacy Instrument developed and pretested in this study. Selected health behaviours (eating, teeth brushing, smoking, and alcohol consumption) were measured using self-report scales. Chi-square tests were conducted to measure differences between DHL and health behaviour. Results Associations were found between DHL and all eating behaviours (fruits; vegetables and salad; whole-grain products; other animal-based products; chocolate or other sweets; sugary drinks; fast food), except for eating meat and sausages. Schoolchildren with higher levels of DHL reported more often about regular consumption of fruits and vegetables (X2 (2)=17.06, p = <.001). salads (X2 (2)=56.54 p = <.001) and whole-grain-products (X2 (2)=98.81 p = <.001). While DHL was associated with teeth brushing (X2 (2)=44.46, p = <.001), no differences were observed for smoking (X2 (2)=1.93, p=.381) and drinking alcohol within the last 30 days (X2 (2)=2.62, p=.270). Conclusions These findings indicate that most health behaviours of schoolchildren may benefit from enhancing DHL in schools. Programs should build around these topics. However, more research is needed to investigate associations between DHL and health behaviours comprehensively.

Social patterning of health misinformation in two Eastern Mediterranean populations

Abstract Background Health misinformation, the spread of false or misleading information relevant to health, has been proposed as a major global public health thread by the WHO. We aimed to identify the major social determinants of health misinformation in the general Greek and Cypriot populations. Methods Following proportional quota sampling we recruited a nationwide sample of 585 adults from Greece and Cyprus between January 2022 and May 2023. A newly developed, culturally adopted questionnaire comprising 48 items, was used to assess misinformation on COVID-19 vaccines and the pandemic. Sociodemographic determinants of interest included gender, age, marital status, area of residence, educational attainment, and income. Multiple linear regression was used to determine associations between the aforementioned social factors and the two dimensions of health misinformation, applying mutual adjustment. Results Misinformation about both vaccination and the pandemic was higher in younger age groups (p-trend 0.026 and 0.007, respectively), among those separated, divorced, or widowed (mean difference, 95% CI compared to those single: 9.73, 0.45, 19.01), and among those living in semi-urban compared to urban areas (11.14, 1.32; 20.97 and 9.44, 1.96; 16.92, respectively). We also detected strong inverse socioeconomic gradients in health misinformation based on educational attainment and income (p-trend <0.001, for both). Conclusions Younger individuals, those living alone, those residing in semi-urban areas, and those with lower educational attainment and income are particularly prone to health misinformation. Our adjusted models show that this social phenomenon is not simply explained by differences in education, hence more complex, cultural, political, perceptual, and psychosocial dynamics might be in place. Addressing the social patterning of health misinformation would help manage the issue more effectively and also reduce health inequalities. Key messages • Health misinformation is strongly socially patterned in two Eastern Mediterranean European populations. • Targeting efforts to tackle health misinformation to those more vulnerable, would render such programmes more effective, also helping reduce social inequalities in health.

Improved algorithm for fracture-dissolution pore detection in resistivity imaging logging based on dung beetle optimization

Abstract Resistivity imaging logging has become a direct and precise method for visualizing the structural complexities of reservoir fractures and dissolution pores. The current use of Otsu's thresholding for segmentation results in poor segmentation quality and significant noise. Accurate segmentation of sub-images containing fracture and dissolution pore targets is essential for automated structure identification and subsequent parameter calculation. This study leverages the rapid convergence and robust global optimization capabilities of the Dung Beetle Optimizer to develop enhanced image segmentation approaches. Specifically, it introduces a refined K-Means algorithm for multi-category image segmentation and an Otsu algorithm for multi-threshold image segmentation, both optimized by the Dung Beetle Optimizer. Compared to conventional binary segmentation algorithms, this new algorithm effectively isolates noise and extracts multi-category information. Using the segmented sub-images, this paper integrates mathematical morphology techniques to compute parameters such as area, perimeter, tortuosity length, and pore shape factor for identified targets. Additionally, Principal Component Analysis is used to derive recognition factors for fractures and dissolution pores. Applications show that this factor can identify matrix, fracture, and dissolution pore targets in complex background images. By combining parameter information of the target area, the method effectively removes false information in resistivity imaging and segments sub-images of fractures and dissolution pores, calculating fracture area ratio, dissolution pore area ratio, and total area ratio.

ChatGPT as a Source of Information about Russian Military Involvement in Ukraine (2014–Present)

The current online environment has seen an explosion of false news and conspiracy theories, and questions have been raised as to whether Large Language Models or Large Generative Artificial Intelligence Models such as ChatGPT could be used to generate false information. Against this background, the current study investigated whether ChatGPT could be used as a reliable source of information about Russian military involvement in Ukraine (2014– present). Based on previous research, seven Russian narratives that have justified Russian military involvement in Ukraine (from a Russian perspective) were identified and ChatGPT was tasked with generating 10 responses to 10 questions posed around these narratives. Responses were scored for truthfulness by two annotators. Overall, the study found that ChatGPT does not generate misinformation, and on average, truthfulness was scored at 3.19/4. It is also shown how ChatGPT's responses differed between questions, with those relating to Russian claims about Ukrainian atrocities in the Donbas and the reliability of Russian media channels scoring lower on truthfulness, and those relating to the reliability of the Western mainstream media scoring the highest. Generally, ChatGPT's responses pointed to reliable and trustworthy sources of information about this conflict, suggesting that this and similar technologies could be employed to combat misinformation.

COUNTERING DISINFORMATION POLICY: CHALLENGES FOR UKRAINE’S NATIONAL SECURITY

he article examines the problems of combating disinformation in the conditions of a modern full-scale war and overcoming the challenges facing the national security of Ukraine. The concept of disinformation, its impact on public consciousness and the key mechanisms of the spread of false information are outlined. The main directions of the policy of combating disinformation aimed at ensuring information security and resistance to information attacks have been studied. The importance of the development of media literacy among the population as one of the main tools for countering disinformation campaigns through educational programs and social interaction is revealed. The experience of combating disinformation in the developed countries of the world, the USA and the countries of the European Union, is analyzed. The role of state and international initiatives, the cooperation of governments with technology companies, as well as the implementation of legislative mechanisms are highlighted. The main tools aimed at regulating the spread of false information in the information space are revealed. The study emphasizes the importance of active cooperation with international partners to ensure an effective fight against disinformation at the global level. Special attention is paid to the role of international organizations in the formation of a unified strategy for countering disinformation attacks. Prospects for attracting international support for the development of national information protection systems and Ukraine's participation in global information security initiatives are being considered. Proposed means of an effective policy of combating disinformation, which combine legislative, technical and educational measures. The methods of ensuring resistance to external information threats are characterized. Particular attention is paid to media literacy programs, which have become important elements of national strategies in the fight against fakes and disinformation attacks. The article considers the possibilities of implementing international experience in Ukraine with the aim of strengthening national information security. The expediency of developing complex programs, including the strengthening of modern means of monitoring the information space and raising the level of critical thinking among the population, is analyzed. Emphasis is placed on the need to create a national security strategy for combating disinformation, which will allow effective response to new threats and ensure information security in the conditions of modern warfare.