Disinformation detection on social media: An integrated approach

A review on fake news detection 3T's: typology, time of detection, taxonomies

Fake news has become an industry on its own, where users paid to write fake news and create clickbait content to allure the audience. Apparently, the detection of fake news is a crucial problem and several studies have proposed machine-learning-based techniques to combat fake news. Existing surveys present the review of proposed solutions, while this survey presents several aspects that are required to be considered before designing an effective solution. To this aim, we provide a comprehensive overview of false news detection. The survey presents (1) a clarity to problem definition by explaining different types of false information (like fake news, rumor, clickbait, satire, and hoax) with real-life examples, (2) a list of actors involved in spreading false information, (3) actions taken by service providers, (4) a list of publicly available datasets for fake news in three different formats, i.e., texts, images, and videos, (5) a novel three-phase detection model based on the time of detection, (6) four different taxonomies to classify research based on new-fangled viewpoints in order to provide a succinct roadmap for future, and (7) key bibliometric indicators. In a nutshell, the survey focuses on three key aspects represented as the three T's: Typology of false information, Time of detection, and Taxonomies to classify research. Finally, by reviewing and summarizing several studies on fake news, we outline some potential research directions.

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.