Multimodal Fake News Detection

Abstract

Over the last few years, there has been an unprecedented proliferation of fake news. As a consequence, we are more susceptible to the pernicious impact that misinformation and disinformation spreading can have on different segments of our society. Thus, the development of tools for the automatic detection of fake news plays an important role in the prevention of its negative effects. Most attempts to detect and classify false content focus only on using textual information. Multimodal approaches are less frequent and they typically classify news either as true or fake. In this work, we perform a fine-grained classification of fake news on the Fakeddit dataset, using both unimodal and multimodal approaches. Our experiments show that the multimodal approach based on a Convolutional Neural Network (CNN) architecture combining text and image data achieves the best results, with an accuracy of 87%. Some fake news categories, such as Manipulated content, Satire, or False connection, strongly benefit from the use of images. Using images also improves the results of the other categories but with less impact. Regarding the unimodal approaches using only text, Bidirectional Encoder Representations from Transformers (BERT) is the best model, with an accuracy of 78%. Exploiting both text and image data significantly improves the performance of fake news detection.

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

“… The previous methods can be distilled into the schema illustrated in the above figures [ 18 , 19 , 20 ]. …”

Fake News Detection Techniques on Social Media: A Survey

“…Because fake news usually contains both genuine and incorrect assertions, probabilistic models may be a better choice for predicting the possibility of it being fake news than just providing a binary value. Class labels (such as false vs. genuine news) may be predicted by using the same distribution of features that were used to store them in the first place [49]. Each factor, such as the reliability of the source, the nature of the news, or the response of the public, has unique limits in terms of accurately anticipating false news on its own, making it very difficult to detect false news [50].…”

“…User information on Facebook tends to be selected in ways that are consistent with their system of ideas, leading to the establishment of polarized groups, sometimes known as echo chambers, according to recent results [3]. Users on social media sites such as Facebook, for example, always follow others who share their interests and, as a result, get news that supports their preferred established narratives [49]. Many psychological variables contribute to the process by which individuals consume and trust bogus news that contributes to the echo chamber effect.…”

EFND: A Semantic, Visual, and Socially Augmented Deep Framework for Extreme Fake News Detection

“…These attributes were employed as statistical characteristics in an ensemble model comprising pre-trained models, a statistical feature fusion network, a unique heuristic approach, and news article variables. Segura-Bedmar and Alonso-Bartolome [52] categorized fake news using unimodal and multimodal approaches. Their multimodal technique integrates text and image data based on CNN architecture.…”