Predicting image credibility in fake news over social media using multi-modal approach

Multi-Modal Fake News Detection via Bridging the Gap between Modals

Multi-modal fake news detection aims to identify fake information through text and corresponding images. The current methods purely combine images and text scenarios by a vanilla attention module but there exists a semantic gap between different scenarios. To address this issue, we introduce an image caption-based method to enhance the model's ability to capture semantic information from images. Formally, we integrate image description information into the text to bridge the semantic gap between text and images. Moreover, to optimize image utilization and enhance the semantic interaction between images and text, we combine global and object features from the images for the final representation. Finally, we leverage a transformer to fuse the above multi-modal content. We carried out extensive experiments on two publicly available datasets, and the results show that our proposed method significantly improves performance compared to other existing methods.

Understanding image-text relations and news values for multimodal news analysis

The analysis of news dissemination is of utmost importance since the credibility of information and the identification of disinformation and misinformation affect society as a whole. Given the large amounts of news data published daily on the Web, the empirical analysis of news with regard to research questions and the detection of problematic news content on the Web require computational methods that work at scale. Today's online news are typically disseminated in a multimodal form, including various presentation modalities such as text, image, audio, and video. Recent developments in multimodal machine learning now make it possible to capture basic "descriptive" relations between modalities-such as correspondences between words and phrases, on the one hand, and corresponding visual depictions of the verbally expressed information on the other. Although such advances have enabled tremendous progress in tasks like image captioning, text-to-image generation and visual question answering, in domains such as news dissemination, there is a need to go further. In this paper, we introduce a novel framework for the computational analysis of multimodal news. We motivate a set of more complex image-text relations as well as multimodal news values based on real examples of news reports and consider their realization by computational approaches. To this end, we provide (a) an overview of existing literature from semiotics where detailed proposals have been made for taxonomies covering diverse image-text relations generalisable to any domain; (b) an overview of computational work that derives models of image-text relations from data; and (c) an overview of a particular class of news-centric attributes developed in journalism studies called news values. The result is a novel framework for multimodal news analysis that closes existing gaps in previous work while maintaining and combining the strengths of those accounts. We assess and discuss the elements of the framework with real-world examples and use cases, setting out research directions at the intersection of multimodal learning, multimodal analytics and computational social sciences that can benefit from our approach.

A Systematic Literature Review and Meta-Analysis of Studies on Online Fake News Detection

The ubiquitous access and exponential growth of information available on social media networks have facilitated the spread of fake news, complicating the task of distinguishing between this and real news. Fake news is a significant social barrier that has a profoundly negative impact on society. Despite the large number of studies on fake news detection, they have not yet been combined to offer coherent insight on trends and advancements in this domain. Hence, the primary objective of this study was to fill this knowledge gap. The method for selecting the pertinent articles for extraction was created using the preferred reporting items for systematic reviews and meta-analyses (PRISMA). This study reviewed deep learning, machine learning, and ensemble-based fake news detection methods by a meta-analysis of 125 studies to aggregate their results quantitatively. The meta-analysis primarily focused on statistics and the quantitative analysis of data from numerous separate primary investigations to identify overall trends. The results of the meta-analysis were reported by the spatial distribution, the approaches adopted, the sample size, and the performance of methods in terms of accuracy. According to the statistics of between-study variance high heterogeneity was found with τ2 = 3.441; the ratio of true heterogeneity to total observed variation was I2 = 75.27% with the heterogeneity chi-square (Q) = 501.34, the degree of freedom = 124, and p ≤ 0.001. A p-value of 0.912 from the Egger statistical test confirmed the absence of a publication bias. The findings of the meta-analysis demonstrated satisfaction with the effectiveness of the recommended approaches from the primary studies on fake news detection that were included. Furthermore, the findings can inform researchers about various approaches they can use to detect online fake news.

MCred: multi-modal message credibility for fake news detection using BERT and CNN

Online social media enables low cost, easy access, rapid propagation, and easy communication of information, including spreading low-quality fake news. Fake news has become a huge threat to every sector in society, and resulting in decrements in the trust quotient for media and leading the audience into bewilderment. In this paper, we proposed a new framework called Message Credibility (MCred) for fake news detection that utilizes the benefits of local and global text semantics. This framework is the fusion of Bidirectional Encoder Representations from Transformers (BERT) using the relationship between words in sentences for global text semantics, and Convolutional Neural Networks (CNN) using N-gram features for local text semantics. We demonstrate through experimental results a popular Kaggle dataset that MCred improves the accuracy over a state-of-the-art model by 1.10% thanks to its combination of local and global text semantics.

A systematic literature review and existing challenges toward fake news detection models

Emerging of social media creates inconsistencies in online news, which causes confusion and uncertainty for consumers while making decisions regarding purchases. On the other hand, in existing studies, there is a lack of empirical and systematic examination observed in terms of inconsistency regarding reviews. The spreading of fake news and disinformation on social media platforms has adverse effects on stability and social harmony. Fake news is often emerging and spreading on social media day by day. It results in influencing or annoying and also misleading nations or societies. Several studies aim to recognize fake news from real news on online social media platforms. Accurate and timely detection of fake news prevents the propagation of fake news. This paper aims to conduct a review on fake news detection models that is contributed by a variety of machine learning and deep learning algorithms. The fundamental and well-performing approaches that existed in the past years are reviewed and categorized and described in different datasets. Further, the dataset utilized, simulation platforms, and recorded performance metrics are evaluated as an extended review model. Finally, the survey expedites the research findings and challenges that could have significant implications for the upcoming researchers and professionals to improve the trust worthiness of automated fake news detection models.

IFND: a benchmark dataset for fake news detection

Spotting fake news is a critical problem nowadays. Social media are responsible for propagating fake news. Fake news propagated over digital platforms generates confusion as well as induce biased perspectives in people. Detection of misinformation over the digital platform is essential to mitigate its adverse impact. Many approaches have been implemented in recent years. Despite the productive work, fake news identification poses many challenges due to the lack of a comprehensive publicly available benchmark dataset. There is no large-scale dataset that consists of Indian news only. So, this paper presents IFND (Indian fake news dataset) dataset. The dataset consists of both text and images. The majority of the content in the dataset is about events from the year 2013 to the year 2021. Dataset content is scrapped using the Parsehub tool. To increase the size of the fake news in the dataset, an intelligent augmentation algorithm is used. An intelligent augmentation algorithm generates meaningful fake news statements. The latent Dirichlet allocation (LDA) technique is employed for topic modelling to assign the categories to news statements. Various machine learning and deep-learning classifiers are implemented on text and image modality to observe the proposed IFND dataset's performance. A multi-modal approach is also proposed, which considers both textual and visual features for fake news detection. The proposed IFND dataset achieved satisfactory results. This study affirms that the accessibility of such a huge dataset can actuate research in this laborious exploration issue and lead to better prediction models.