Ensemble machine learning approaches for fake news classification

The online spread of fake news on various platforms has emerged as a significant concern, posing threats to public opinion, political stability, and the dissemination of reliable information. Researchers have turned to advanced technologies, including machine learning (ML) and deep learning (DL) techniques, to detect and classify fake news to address this issue. This research study explores fake news classification using diverse ML and DL approaches. We utilized a well-known “Fake News” dataset sourced from Kaggle, encompassing a labelled news collection. We implemented diverse ML models, including multinomial naïve bayes (MNB), gaussian naïve bayes (GNB), Bernoulli naïve Bayes (BNB), logistic regression (LR), and passive aggressive classifier (PAC). Additionally, we explored DL models, such as long short-term memory (LSTM), convolutional neural networks (CNN), and CNN-LSTM. We compared the performance of these models based on key evaluation metrics, such as accuracy, precision, recall, and the F1 score. Additionally, we conducted cross-validation and hyperparameter tuning to ensure optimal performance. The results provide valuable insights into the strengths and weaknesses of each model in classifying fake news. We observed that DL models, particularly LSTM and CNN-LSTM, showed better performance compared to traditional ML models. These models achieved higher accuracy and demonstrated robustness in classification tasks. These findings emphasize the potential of DL models to tackle the spread of fake news effectively and highlight the importance of utilizing advanced techniques to address this challenging problem.

Misinformation becomes rampant in the digital age and social media provide people with the opportunities for engaging more actively in society. The objectives of the study are: (i) to ascertain the extent to which residents of Kano have been exposed to digital images on Covid-19 that often accompany fake news in social media; (ii) to establish the extent to which residents of Kano are influenced by fake news on Covid-19 with images; (iii) to find out the factors that often lead to the influence of fake news with digital images on Covid-19 among social media users in Kano; (iv) to ascertain the social media platforms mostly used in spreading fake news about Covid-19 in the state. Theoretically, Technological Determinism and Perception theories were adopted to analyze these issues. A Positivist approach to data generation and analysis was adopted using the survey method. Two local governments were selected for the study: Tarauni and Kano Municipal. Tarauni local government area had the highest number of the Covid-19 cases, while Kano Municipal had the lowest number. The population of the study consist of 593,087 with a sample size of 400 respondents derived from Taro Yamane’s sample size prediction table. The respondents were reached through cluster sampling. A total of 400 copies of questionnaires were administered to respondents in Tarauni and Kano Municipal. However, only 385 copies, which represent (96%), were retrieved and found usable for the study as the remaining 15 were not returned. The study found that Kano residents were significantly exposed to digital images that often accompany fake news in social media. They read news online every day, prefer news accompanied by images, share and like news online. The study also found that Kano residents are influenced by fake news with digital images on Covid-19 to a very great extent, especially on Facebook. Factors responsible for proliferation of fake news on social media include: perception or instinct, eagerness to be the first to share images and lack of knowledge about image verification tools. The study concludes that ignorance and the old belief that pictures do not lie were responsible for this.

The proliferation of fake news is one of the major problems that causes personal and societal harm. In today’s fast-paced digital age, misinformation spreads rapidly, often leaving individuals without the time to verify the authenticity of the information. This can cause irreparable damage to personal reputations and organizational credibility. Thus, instigated by the quintessential necessity, there is a dire need to construct a framework for the automatic detection and identification of fake news at its inception. This research presents a novel approach that leverages a combination of three popular word embeddings (FastText, FastText-Subword, and GloVe) integrated with a customized convolutional neural-network(CNN) to classify fake news accurately. The proposed model was tested against the Fake News Challenge dataset. Hundreds of word vector features were generated from the combined embedding and then managed with PCA and significant features were extracted. The proposed model gives an accuracy of 94.58%, 95.35% precision, 97.29% recall, and an F1 score of 96.11%. The proposed framework’s robustness is demonstrated when compared with other machine, deep, and ensemble learning approaches, showing superior performance. Furthermore, the effectiveness of the model is validated on an independent Arabic Fake News dataset.

Machine learning methods are proposed to mitigate the spread of fake Brazilian news about politics so as not to harm society. Supervised algorithms are explored, requiring labeled news to train. However, labeling a high volume of news can be complex, onerous, time-consuming, error-prone, and costly. Hence, large language models (LLMs) have been used to detect fake news once LLMs are unsupervised methods that can play the role of classifiers. Most fake news detection studies explore the OpenAI LLMs (require payment) and lack an empirical evaluation with other LLMs. However, several open-source models obtain comparative and state-of-the-art (SOTA) results. We highlight that these models have yet to be explored in detecting fake Brazilian news about politics, which is crucial as it directly impacts society. In this sense, we propose a new dataset for detecting fake Brazilian news about politics and an empirical evaluation of open-source LLMs and OpenAI LLMs. In our results, the LLM from Google (Gemma) outperformed the other six LLMs, including GPT-4, proving to be the most promising model for detecting fake news about Brazilian politics.

The proliferation of fake news across multiple modalities has emerged as a critical challenge in the modern information landscape, necessitating advanced detection methods. This study proposes a comprehensive framework for fake news detection integrating text, images, and videos using machine learning and deep learning techniques. The research employs a dual-phased methodology, first analyzing textual data using various classifiers, then developing a multimodal approach combining BERT for text analysis and a modified CNN for visual data. Experiments on the ISOT fake news dataset and MediaEval 2016 image verification corpus demonstrate the effectiveness of the proposed models. For textual data, the Random Forest classifier achieved 99% accuracy, outperforming other algorithms. The multimodal approach showed superior performance compared to baseline models, with a 3.1% accuracy improvement over existing multimodal techniques. This research contributes to the ongoing efforts to combat misinformation by providing a robust, adaptable framework for detecting fake news across different media formats, addressing the complexities of modern information dissemination and manipulation.

The availability and expansion of social media has made it difficult to distinguish between fake and real news. Information falsification has exponentially increased as a result of how simple it is to spread information through sharing. Social media dependability is also under jeopardy due to the extensive dissemination of false information. Therefore, it has become a research problem to automatically validate information, specifically source, content, and publisher, to identify it as true or false. Despite its limitations, machine learning (ML) has been crucial in the categorization of information. Previous studies suggested three-step methods for categorising false information on social media. In the first step of the process, the data set is subjected to a number of pre-processing processes in order to transform unstructured data sets into structured data sets. The unknowable properties of fake news and the features are extracted by the Lexicon Model in the second stage. In the third stage of this research project, a feature selection method by WOA (Whale Optimization Algorithm) for weight value to tune the classification part. Finally, a Hybrid Classification model that is hybrid with a fuzzy based Convolutional Neural Network and kernel based support vector machine is constructed in order to identify the data pertaining to bogus news. However using single classifier for fake news detection produces the insufficient accuracy. To overcome this issue in this work introduced an improved model for fake news classification. To turn unstructured data sets into structured data sets, a variety of pre-processing operations are used on the data set in the initial phase of the procedure. The unknowable properties of fake news and the features are extracted by the Lexicon Model in the second stage. In the third stage of this research project, a feature selection method by COA (Coati Optimization Algorithm) for weight value to tune the classification part. Finally, an ensemble of RNN (Recurrent Neural Networks), VGG-16 and ResNet50.A classification model was developed to recognise bogus news information. Evaluate each fake news analysis' performance in terms of accuracy, precision, recall, and F1 score. The suggested model, out of all the methodologies taken into consideration in this study, provides the highest outcomes, according to experimental findings

The World Wide Web's introduction, as well as the rapid adoption of social media platforms (such as Facebook and Twitter), paved the way for unprecedented levels of knowledge distribution in human history. Certain entities, however, take advantage of such platforms, sometimes for monetary gain and sometimes for the purpose of promoting prejudiced viewpoints, changing mindsets, and disseminating satire or ridiculousness. This phenomenon is known as fake news. Because the spread of fake news can have serious consequences, such as election rigging and widening political divides, developing methods to detect fake news content is critical. A computerised classification system is used to classify a wide range of things. Fake news is a term used to describe this occurrence. Given the serious consequences of fake news, such as swaying elections and widening political divides, developing methods for detecting fake news content is critical. It is difficult to automate the classification of a text article as misinformation or disinformation. We suggest employing a machine learning ensemble approach for automatic classification in this paper. Our research looks into various textual properties such as word counts, term frequency, and inverse document frequency that can be used to distinguish between fake and real content. We train a Passive-Aggressive Classifier and evaluate its performance on real-world datasets using these properties. The datasets will be used in part to train and part to test the classifiers. It is possible to determine whether the news is fake or not by testing the different features of the datasets on the classifier.

In our modern society where the internet is ubiquitous, everyone relies on various online resources for news. Along with the internet in the use of social media platforms like Facebook, Dataset, WhatsApp etc. News spread rapidly among millions of users within a very short span of time. The spread of fake news has far-reaching consequences like the creation of based opinions to swaying election outcomes for the benefit of certain candidates. Moreover, spammers use appealing news headlines to generate revenue using advertisement via click- baits. In this project we aim to perform classification of various news article available online with the help of concepts of Machine Learning. We aim to provide the user with the ability to classify the news which is fake or real with the help of some algorithm used in Machine Learning. This work purposes the use of machine learning techniques to detect Fake news. In the experiments used: Support Vector Machine (SVM). The normalization method is important step for cleansing data before using the machine learning method to classify data. We are aiming Support Vector Machine result should reach the higher accuracy level. Besides of machine learning we are using HTML, Python each one of has it's individual purpose for successful creation to build fake news detection KEYWORDS: Internet, Social Media, Fake News, Classification, Artificial Intelligence, Machine Learning, Websites, Python, HTML.

Landslide disaster risk reduction necessitates the investigation of different geotechnical causal factors for slope failures. Machine learning (ML) techniques have been proposed to study causal factors across many application areas. However, the development of ensemble ML techniques for identifying the geotechnical causal factors for slope failures and their subsequent prediction has lacked in literature. The primary goal of this research is to develop and evaluate novel feature selection methods for identifying causal factors for slope failures and assess the potential of ensemble and individual ML techniques for slope failure prediction. Twenty-one geotechnical causal factors were obtained from 60 sites (both landslide and non-landslide) spread across a landslide-prone area in Mandi, India. Relevant causal factors were evaluated by developing a novel ensemble feature selection method that involved an average of different individual feature selection methods like correlation, information-gain, gain-ratio, OneR, and F-ratio. Furthermore, different ensemble ML techniques (Random Forest (RF), AdaBoost (AB), Bagging, Stacking, and Voting) and individual ML techniques (Bayesian network (BN), decision tree (DT), multilayer perceptron (MLP), and support vector machine (SVM)) were calibrated to 70% of the locations and tested on 30% of the sites. The ensemble feature selection method yielded six major contributing parameters to slope failures: relative compaction, porosity, saturated permeability, slope angle, angle of the internal friction, and in-situ moisture content. Furthermore, the ensemble RF and AB techniques performed the best compared to other ensemble and individual ML techniques on test data. The present study discusses the implications of different causal factors for slope failure prediction.

Fake Antitrust?: Fact Checking on the Alleged Competition Law Case Against Social Media (Facebook) for the Proliferation of Fake News

'Cure or Poison?' Identity Verification and the Spread of Fake News on Social Media

Elections worldwide have been marked by the spread of fake news. Online disinformation is everywhere, used as a political weapon in the battlefield of manipulation. This study focused on the Portuguese 2019 elections to assess the reach of fake news compared to mainstream media news and to verify whether fake news had specific targets. We reviewed all posts (N=1197) from newspaper Facebook pages and fake news Facebook pages published during the campaign to verify their engagement. BuzzSumo assessed popularity by counting all posts’ shares, reactions and comments. Iramuteq software related the content of all published headlines by analyzing clusters of the most frequent words. Findings show that fake news had no greater reach than real news during the election campaign. However, fake news are more likely to be shared, while real news tend to get more reactions and more comments. In fake news headlines the terms associated with left-wing and government are the most common. The prime minister and the Socialist Party are associated with negative connotations. Results suggest that Portuguese fake news are related to rightwing extremism and publish hate content targeting corruption and leftist policies in general. Unlike other countries, anti-immigration discourse and fearmongering were not prominent contents.

Behind the cues: A benchmarking study for fake news detection

Easy access to equipment, software, and platforms to create, distribute, and provide access to fake news stories has exacerbated the problem of fake news, making for a large number of highly biased sources that are reaching the mainstream through social networks. The economics of emotion theory proposes that fake news headlines are created to evoke emotional responses in readers that will cause them to interact with the article in a way that allows the creator to make a profit (through clicking on the link to the full article, by sharing the article, etc.). This mixed methods study investigates the process by which individuals experience discrete emotional reactions to fake news headlines, and how these emotions contribute to the perpetuation of fake news through sharing behaviors. U.S. participants (n=879 across two waves) viewed one of eight false news headlines and reported their emotional reactions, belief in the headline, and potential sharing behaviors. In general, participants were more likely to believe headlines that aligned with their existing beliefs (e.g., liberals were more likely to believe negative news about conservatives), reacted with more negative emotions to headlines that attacked their party, and were more likely to report intentions to suppress (e.g., post a link to a fact check) fake news that attacked their own party. Emotional reactivity of participants was associated with response behavior intentions such that participants who reported high levels of emotions were more likely to take actions that would spread or suppress the fake news, participants who reported low levels of emotions were more likely to ignore or disengage from the spread of false news, and participants who reported high levels of negative emotions and low levels of positive emotions were more likely to suppress the spread of fake news and less likely to contribute to the spread of fake news. Our findings are synthesized into a process model that explains how discrete emotions and beliefs influence sharing behaviors. Implications for mitigating the spread of fake news are discussed in terms of this model.

Political Science There was a proliferation of fake news during the 2016 election cycle. Grinberg et al. analyzed Twitter data by matching Twitter accounts to specific voters to determine who was exposed to fake news, who spread fake news, and how fake news interacted with factual news (see the Perspective by Ruths). Fake news accounted for nearly 6% of all news consumption, but it was heavily concentrated—only 1% of users were exposed to 80% of fake news, and 0.1% of users were responsible for sharing 80% of fake news. Interestingly, fake news was most concentrated among conservative voters. Science , this issue p. [374][1]; see also p. [348][2] [1]: /lookup/doi/10.1126/science.aau2706 [2]: /lookup/doi/10.1126/science.aaw1315