Automatic Fake News Detection Research Articles

Perspective Collaboration for Multi-domain Fake News Detection

Fake news is widely spread on social media. Much research works have been done on automatic fake news detection in single domain. However, fake news exists in various domains, so the detection model based on single domain is less effective in multiple domain scenes. To improve the detection ability of multi-domain fake news, we propose a perspective collaboration for multi-domain fake news detection (PCMFND) method to detect fake news across multiple domains by combining the powerful feature extraction ability of expert systems. The method extracts features of different perspectives from news content separately, then interactively combines the features of different perspectives, and ultimately achieves fake news detection by adaptively aggregating features of each perspective through domain knowledge. The effectiveness of the proposed method is demonstrated through comparison experiments with traditional multi-domain detection methods on Chinese and English multi-domain datasets.

Unveiling Implicit Deceptive Patterns in Multi-Modal Fake News via Neuro-Symbolic Reasoning

In the current Internet landscape, the rampant spread of fake news, particularly in the form of multi-modal content, poses a great social threat. While automatic multi-modal fake news detection methods have shown promising results, the lack of explainability remains a significant challenge. Existing approaches provide superficial explainability by displaying learned important components or views from well-trained networks, but they often fail to uncover the implicit deceptive patterns that reveal how fake news is fabricated. To address this limitation, we begin by predefining three typical deceptive patterns, namely image manipulation, cross-modal inconsistency, and image repurposing, which shed light on the mechanisms underlying fake news fabrication. Then, we propose a novel Neuro-Symbolic Latent Model called NSLM, that not only derives accurate judgments on the veracity of news but also uncovers the implicit deceptive patterns as explanations. Specifically, the existence of each deceptive pattern is expressed as a two-valued learnable latent variable, which is acquired through amortized variational inference and weak supervision based on symbolic logic rules. Additionally, we devise pseudo-siamese networks to capture distinct deceptive patterns effectively. Experimental results on two real-world datasets demonstrate that our NSLM achieves the best performance in fake news detection while providing insightful explanations of deceptive patterns.

Retraction Note: Hybrid deep learning model for automatic fake news detection

Retraction Note: Hybrid deep learning model for automatic fake news detection

Automatic Detection of Fake News Using Gated Recurrent Unit Deep Model

Nowadays, the utilization of social media platforms continues to rise, as is the dissemination of misleading data. This fake information is damaging to both society and individuals. Hence, it is essential to prevent and detect the dissemination of fake news. Furthermore, the main challenge is the lack of an effective technique for distinguishing between truthful and false reviews; even individuals are usually unable to recognize the difference. In contract to numerous machine learning-based methods, the deep learning-based methods exhibit a superior capacity for accurately detecting fake news. Earlier studies focused on machine learning based and data mining techniques, with limited exploration of deep learning-based methods for automated detecting fake news task. This study attempts to introduce a method based on the GRU deep model in order to detect automatically fake news. Experimental evaluation using a benchmark fake news dataset indicates extremely encouraging results and enhanced performances.

Automatic detection of fake news using recurrent neural network—Long short-term memory

<p>The propagation of deliberate misinformation is gaining significant momentum, especially across different social media platforms. Despite the fact that there are several fact-checking blogs and websites that distinguish between news that is genuine or fake, and regardless of the reality that there is ongoing research being conducted to restrict the propagation of fake news, the issue is still one that needs to be addressed. The most major barrier is a failure to spot monitors and to disclose false news in a reasonable timeframe, both of which are critical components. In this research, a system is proposed that utilizes deep learning model of Recurrent Neural Network—Long Short-Term Memory (RNN-LSTM) in order to put an end to the circulation of misleading information and put a stop to, and expose instances of fake news that are spread through reliable channels. The process of extracting hybrid features from text data, such as Lemmas, Bi-Gram, Tri-Gram, N-gram, Term Frequency Inverse Document Frequency (TF-IDF), part-of-speech, and dependency-based natural language processing features, is developed as a strategy. When compared to other traditional approaches to machine learning classifier, the RNN-LSTM method that was proposed obtains a greater level of accuracy than those other approaches. It achieves an accuracy rate of 99.10% both during training and testing, which is better to the accuracy achieved by common machine learning approaches such as Support Vector Machine (SVM), Artificial Neural Network (ANN), Random Forest (RF), Naïve Bayes (NB), and Decision Tree (DT). In the proposed approach for detecting false news using RNN-LSTM, the three experiments are conducted to acquire, accuracy, precision, recall, and F-score with varying forms of cross validation (5-Fold, 10-Fold and 15-Fold). Based on the findings of the empirical research, the conclusion can be drawn that the RNN-LSTM with ReLu function provides more accurate detection than both the RNN-LSTM (Tan h) function and the RNN-LSTM (sigmoid) function with 15 fold cross validation.<strong></strong></p>

The PolitiFact-Oslo Corpus: A New Dataset for Fake News Analysis and Detection

This study presents a new dataset for fake news analysis and detection, namely, the PolitiFact-Oslo Corpus. The corpus contains samples of both fake and real news in English, collected from the fact-checking website PolitiFact.com. It grew out of a need for a more controlled and effective dataset for fake news analysis and detection model development based on recent events. Three features make it uniquely placed for this: (i) the texts have been individually labelled for veracity by experts, (ii) they are complete texts that strictly correspond to the claims in question, and (iii) they are accompanied by important metadata such as text type (e.g., social media, news and blog). In relation to this, we present a pipeline for collecting quality data from major fact-checking websites, a procedure which can be replicated in future corpus building efforts. An exploratory analysis based on sentiment and part-of-speech information reveals interesting differences between fake and real news as well as between text types, thus highlighting the importance of adding contextual information to fake news corpora. Since the main application of the PolitiFact-Oslo Corpus is in automatic fake news detection, we critically examine the applicability of the corpus and another PolitiFact dataset built based on less strict criteria for various deep learning-based efficient approaches, such as Bidirectional Long Short-Term Memory (Bi-LSTM), LSTM fine-tuned transformers such as Bidirectional Encoder Representations from Transformers (BERT) and RoBERTa, and XLNet.

Fake news detection: Taxonomy and comparative study

The proliferation of social networks has presented a significant challenge in combating the pervasive issue of fake news within modern societies. Due to the large amount of information and news produced daily in text, audio, and video, the validation and verification of this information have become crucial tasks. Leveraging advancements in artificial intelligence, distinguishing between fake news and factual information through automatic fake news detection systems has become more feasible. Automatic fake news detection has been explored from diverse perspectives, employing various feature extraction and classification models. Nonetheless, empirical evaluations, categorization, and comparisons of existing techniques for handling this problem remain limited. In this paper, we revisit the definitions and perspectives of fake news and propose an updated taxonomy for the field based on multiple criteria: (1) Type of features used in fake news detection; (2) Fake news detection perspectives; (3) Feature representation methods; and (4) Classification approaches. Moreover, we conduct an extensive empirical study to evaluate several feature representation techniques and classification approaches based on accuracy and computational cost. Our experimental results demonstrate that the optimal feature extraction techniques vary depending on the characteristics of the dataset. Notably, context-dependent models based on transformer models consistently exhibit superior performance. Additionally, employing transformer models as feature extraction methods, rather than solely fine-tuning the network for the downstream task, improves overall performance. Through extensive error analysis, we identify that a combination of feature representation methods and classification algorithms, including classical ones, offer complementary aspects and should be considered for achieving better generalization performance while maintaining a relatively low computational cost. For further details, including source codes, figures, and datasets, please refer to our project’s GitHub repository: [https://github.com/FFarhangian/Fake-news-detection-Comparative-Study].

A comprehensive survey on machine learning approaches for fake news detection

AbstractThe proliferation of fake news on social media platforms poses significant challenges to society and individuals, leading to negative impacts. As the tactics employed by purveyors of fake news continue to evolve, there is an urgent need for automatic fake news detection (FND) to mitigate its adverse social consequences. Machine learning (ML) and deep learning (DL) techniques have emerged as promising approaches for characterising and identifying fake news content. This paper presents an extensive review of previous studies aiming to understand and combat the dissemination of fake news. The review begins by exploring the definitions of fake news proposed in the literature and delves into related terms and psychological and scientific theories that shed light on why people believe and disseminate fake news. Subsequently, advanced ML and DL techniques for FND are dicussed in detail, focusing on three main feature categories: content-based, context-based, and hybrid-based features. Additionally, the review summarises the characteristics of fake news, commonly used datasets, and the methodologies employed in existing studies. Furthermore, the review identifies the challenges current FND studies encounter and highlights areas that require further investigation in future research. By offering a comprehensive overview of the field, this survey aims to serve as a guide for researchers working on FND, providing valuable insights for developing effective FND mechanisms in the era of technological advancements.

A comprehensive review on automatic detection of fake news on social media

A comprehensive review on automatic detection of fake news on social media

Detecting Vietnamese fake news

This paper focuses on constructing a dataset consisting of both fake news and factual news in the Vietnamese language. We employ Deep Learning models, namely Long Short-Term Memory, bidirectional Long Short-Term Memory, and Convolutional Neural Network - bidirectional Long Short-Term Memory, to identify Vietnamese fake news. The performance evaluation of the models includes assessing the prediction ratio Area Under The Curve of each model and providing insights into their computational efficiency. Additionally, these three models evaluate the contribution of deep learning techniques for fake news detection and emphasize the potential for exploring interconnections between neural networks in addressing automatic Vietnamese fake news detection.

AAFNDL - An Accurate Fake Information Recognition Model Using Deep Learning for the Vietnamese Language

On the Internet, "fake news" is a common phenomenon that frequently disturbs society because it contains intentionally false information. The issue has been actively researched using supervised learning for automatic fake news detection. Although accuracy is increasing, it is still limited to identifying fake information through channels on social platforms. This study aims to improve the reliability of fake news detection on social networking platforms by examining news from unknown domains. Especially, information on social networks in Vietnam is difficult to detect and prevent because everyone has equal rights to use the Internet for different purposes. These individuals have access to several social media platforms. Any user can post or spread the news through online platforms. These platforms do not attempt to verify users or the content of their locations. As a result, some users try to spread fake news through these platforms to propagate against an individual, a society, an organization, or a political party. In this paper, we proposed analyzing and designing a model for fake news recognition using Deep learning (called AAFNDL). The method to do the work is: 1) First, we analyze the existing techniques such as Bidirectional Encoder Representation from Transformer (BERT); 2) We proceed to build the model for evaluation; and finally, 3) We approach some Modern techniques to apply to the model, such as the Deep Learning technique, classifier technique and so on to classify fake information. Experiments show that our method can improve by up to 8.72% compared to other methods.

Deep Learning Based Fake News Detection on Social Media

Social media platforms become indispensable channels to discover the latest news by the Internet users. Millions of
 news is broken first, spread faster, and reach larger communities on these platforms in a very short time compared to traditional media organs. However, in contrast to traditional media, social media platforms lack of security in terms of control mechanisms to verify the reliability and accuracy of the disseminated news. This brings the need for automatic fake news detection systems for these platforms to prevent or reduce spread of false information. In this paper, we study the problem of fake news detection on social media for two languages, both of them having distinct linguistic features: Turkish and English. In this regard, we create the first real-world public dataset of Turkish fake and real news tweets, named SOSYalan, to the best of our knowledge. For English language, we carry out experiments with two benchmark datasets, BuzzFeed and ISOT. We develop deep learning based fake news detection systems for both of Turkish and English languages based on convolutional neural networks (CNN), and recurrent neural networks-long short term memory (RNN-LSTM) approaches with Word2vec embedding model. We evaluate the developed systems in terms of accuracy, precision, recall, F1-score, true-negative rate, false-positive rate, and false-negative rate metrics. The results demonstrate that the developed systems for English language produce higher accuracy rates compared to the most of the existing state-of-the-art studies. Additionally, the results confirm the superiority of our systems developed for Turkish language in comparison to very few studies conducted in this area.

A Machine Learning Framework for Automatic Fake News Detection in Indian Tamil News Channels

A Machine Learning Framework for Automatic Fake News Detection in Indian Tamil News Channels

Fake news, disinformation and misinformation in social media: a review.

Online social networks (OSNs) are rapidly growing and have become a huge source of all kinds of global and local news for millions of users. However, OSNs are a double-edged sword. Although the great advantages they offer such as unlimited easy communication and instant news and information, they can also have many disadvantages and issues. One of their major challenging issues is the spread of fake news. Fake news identification is still a complex unresolved issue. Furthermore, fake news detection on OSNs presents unique characteristics and challenges that make finding a solution anything but trivial. On the other hand, artificial intelligence (AI) approaches are still incapable of overcoming this challenging problem. To make matters worse, AI techniques such as machine learning and deep learning are leveraged to deceive people by creating and disseminating fake content. Consequently, automatic fake news detection remains a huge challenge, primarily because the content is designed in a way to closely resemble the truth, and it is often hard to determine its veracity by AI alone without additional information from third parties. This work aims to provide a comprehensive and systematic review of fake news research as well as a fundamental review of existing approaches used to detect and prevent fake news from spreading via OSNs. We present the research problem and the existing challenges, discuss the state of the art in existing approaches for fake news detection, and point out the future research directions in tackling the challenges.

HyproBert: A Fake News Detection Model Based on Deep Hypercontext

News media agencies are known to publish misinformation, disinformation, and propaganda for the sake of money, higher news propagation, political influence, or other unfair reasons. The exponential increase in the use of social media has also contributed to the frequent spread of fake news. This study extends the concept of symmetry into deep learning approaches for advanced natural language processing, thereby improving the identification of fake news and propaganda. A hybrid HyproBert model for automatic fake news detection is proposed in this paper. To begin, the proposed HyproBert model uses DistilBERT for tokenization and word embeddings. The embeddings are provided as input to the convolution layer to highlight and extract the spatial features. Subsequently, the output is provided to BiGRU to extract the contextual features. The CapsNet, along with the self-attention layer, proceeds to the output of BiGRU to model the hierarchy relationship among the spatial features. Finally, a dense layer is implemented to combine all the features for classification. The proposed HyproBert model is evaluated using two fake news datasets (ISOT and FA-KES). As a result, HyproBert achieved a higher performance compared to other baseline and state-of-the-art models.

Veracity Analysis of Romanian Fake News

Today, with so much free information online, it becomes increasingly difficult to make sense of what content is based on fact, half-truths or lies. Furthermore, in accordance with the events (e.g., COVID-19) that are increasingly alarming, the speed of false news spread is unprecedented. Of course, fake news impairs social stability and public trust, which calls for increasing demand for their detection. How to spot as faithful as possible fake news? The response that this article gives, by exploring the textual features using artificial intelligence and machine learning. This research addresses the problem of automatic fake news detection for Romanian language. First, we present a new corpus for automatic fake news detection that contains two subsets of 977 and 29 154 news articles in Romanian, separated according to labelling and collection methods. Second, we explore several text-based approaches for automatic fake news detection by using machine learning and artificial intelligence which resulted in an accuracy of 93%.

Uncovering the truth: A deep learning approach to detecting fake news

Fake news is a growing problem on social media and can have significant negative consequences for individuals and society owing to its accessibility, low cost, and quick distribution. It is difficult to automatically identify bogus news that defies the current content-based analysis techniques. One of the key reasons is that current NLP algorithms still lack common sense, which is frequently necessary for understanding how to read the news. Recent research has demonstrated that the propagation patterns of true and fake news differ on social media. With the potential for automatic fake news detection, this study investigates the use of Deep Learning (DL) models to detect fake news on social media. A Neural Network (NN) model was developed using Natural Language Toolkit (NLTK), TensorFlow, and Natural Language Processing (NLP) for textual analysis. The model was trained on a dataset of fake and real news articles, and was able to achieve high accuracy in identifying fake news. The results of this study suggest that DL models can be valuable tools for detecting fake news on social media.

Automatic Detection of Fake News in Spanish: Ecuadorian Political Satire

La circulación de noticias falsas en internet, especialmente las de sátira política a través de redes sociales, ha afectado a la mayoría de la población ecuatoriana. Este trabajo presenta una metodología basada en el aprendizaje estadístico que detecta de forma precisa y automática noticias falsas en español utilizando técnicas de aprendizaje automático y procesamiento del lenguaje natural. El documento comienza presentando conceptos básicos relacionados con las noticias falsas y trabajos relacionados con su detección automática. La segunda sección explica el proceso de creación del corpus de noticias, procesamiento de los textos, representación numérica con TF-IDF y entrenamiento de algoritmos de clasificación supervisados con dos conjuntos de datos diferentes. Los resultados obtenidos del entrenamiento se analizan en la tercera sección, siendo los modelos con máquinas de soporte vectorial los que ofrecen mejores predicciones, mejorando aproximadamente un 15%, 6% y 3% al rendimiento de los modelos con naive bayes, random forests y árboles boosting respectivamente. Finalmente, las conclusiones de la investigación y el trabajo futuro se presentan en la cuarta sección.

Relationship between new media literacy (NML) and web-based fake news epidemic control: a systematic literature review

Purpose This study aims to investigate the current practices being implemented against the dissemination of fake online news, identify the relationship of new media literacy (NML) with fake news epidemic control and find out the challenges in identifying valid sources of information. Design/methodology/approach To accomplish constructed objectives of this study, a systematic literature review (SLR) was conducted. The authors carried out the “Preferred Reporting Items for the Systematic Review and Meta-analysis” guidelines as a research methodology. The data were retrieved from ten world’s leading digital databases and online tools. A total of 25 key studies published in impact factor (IF) journals were included for systematic review vis-à-vis standard approaches. Findings This study revealed trending practices to control fake news consisted of critical information literacy, civic education, new thinking patterns, fact-checkers, automatic fake news detection tools, employment of ethical norms and deep learning via neural networks. Results of the synthesized studies revealed that media literacy, web literacy, digital literation, social media literacy skills and NML assisted acted as frontline soldiers in combating the fake news war. The findings of this research also exhibited different challenges to control fake news perils. Research limitations/implications This study provides pertinent theoretical contributions in the body of existing knowledge through the addition of valuable literature by conducting in-depth systematic review of 25 IF articles on a need-based topic. Practical implications This scholarly contribution is fruitful and practically productive for the policymakers belonging to different spectrums to effectively control web-based fake news epidemic. Social implications This intellectual piece is a benchmark to address fake news calamities to save the social system and to educate citizens from harms of false online stories on social networking websites. Originality/value This study vivifies new vistas via a reinvigorated outlook to address fake news perils embedded in dynamic, rigorous and heuristic strategies for redefining a predetermined set of social values.

Retweet Prediction Based on Heterogeneous Data Sources: The Combination of Text and Multilayer Network Features

Retweet prediction is an important task in the context of various problems, such as information spreading analysis, automatic fake news detection, social media monitoring, etc. In this study, we explore retweet prediction based on heterogeneous data sources. In order to classify a tweet according to the number of retweets, we combine features extracted from the multilayer network and text. More specifically, we introduce a multilayer framework for the multilayer network representation of Twitter. This formalism captures different users’ actions and complex relationships, as well as other key properties of communication on Twitter. Next, we select a set of local network measures from each layer and construct a set of multilayer network features. We also adopt a BERT-based language model, namely Cro-CoV-cseBERT, to capture the high-level semantics and structure of tweets as a set of text features. We then trained six machine learning (ML) algorithms: random forest, multilayer perceptron, light gradient boosting machine, category-embedding model, neural oblivious decision ensembles, and an attentive interpretable tabular learning model for the retweet-prediction task. We compared the performance of all six algorithms in three different setups: with text features only, with multilayer network features only, and with both feature sets. We evaluated all the setups in terms of standard evaluation measures. For this task, we first prepared an empirical dataset of 199,431 tweets in Croatian posted between 1 January 2020 and 31 May 2021. Our results indicate that the prediction model performs better by integrating multilayer network features with text features than by using only one set of features.