Multiverse: Multilingual Evidence for Fake News Detection

Abstract

The rapid spread of deceptive information on the internet can have severe and irreparable consequences. As a result, it is important to develop technology that can detect fake news. Although significant progress has been made in this area, current methods are limited because they focus only on one language and do not incorporate multilingual information. In this work, we propose Multiverse—a new feature based on multilingual evidence that can be used for fake news detection and improve existing approaches. Our hypothesis that cross-lingual evidence can be used as a feature for fake news detection is supported by manual experiments based on a set of true (legit) and fake news. Furthermore, we compared our fake news classification system based on the proposed feature with several baselines on two multi-domain datasets of general-topic news and one fake COVID-19 news dataset, showing that (in combination with linguistic features) it yields significant improvements over the baseline models, bringing additional useful signals to the classifier.

A System to Ensure Information Trustworthiness in Artificial Intelligence Enhanced Higher Education

“…Therefore, any information assessment system that aims to detect fake news must be language-agnostic. This means that the system must be capable of handling multiple languages, and its methods must be generalizable to other languages as well (Dementieva et al, 2023). Currently, there is limited support for multilingual fake news detection in existing techniques.…”

“…Currently, there is limited support for multilingual fake news detection in existing techniques. However, some techniques (Ahuja & Kumar, 2023;Dementieva et al, 2023;Hammouchi & Ghogho, 2022) attempt to address this problem using a cross-lingual evidence approach. The basic idea behind this approach is that if a news item is true, it should be widespread in different languages and across media with different biases.…”

“…Addressing multilingual capabilities is another critical aspect where EMIAS strives to meet user needs effectively. Given that disinformation is not restrained by language or geographical boundaries (Colomina et al, 2021), it is imperative for an effective solution like EMIAS to be capable of handling multiple languages while maintaining its efficacy across them, an issue highlighted by Dementieva et al (2023).…”