Misinformation detection research has been on the rise over the past decade, yet misinformation is still prevalent today on the Internet. Most recent efforts have focused on automation to easily detect misinformation and compensate for the inability of employees by companies to deal with the large volumes of data that are being generated on the Internet. Machine learning, and in particular, deep learning solutions, have shown promise in tackling misinformation issues.8 Yet, several years of research have demonstrated high accuracy in misinformation detection and revealed that the problem is not monolithic in nature. Attacks such as fake news, satire, and hate news can be classified as misinformation, yet the intent and effect differ for each one of these examples. As such, the effectiveness of deep learning approaches may vary depending on the misinformation that it aims to detect. In fact, many studies develop, train, and use deep learning methods to detect misinformation content by using binary labels (e.g., fake or not fake text).6 The outcome is that assumptions are made about the accuracy of deep learning models that may not reflect reality, such as effectiveness in real-world application and portability across social media platforms.
Abstract:
In recent years, we have witnessed growing interest in using deep learning to detect misinformation. This increased attention is being driven by deep learning technologie...Show MoreMetadata
Abstract:
In recent years, we have witnessed growing interest in using deep learning to detect misinformation. This increased attention is being driven by deep learning technologies’ ability to accurately detect this misinformation. However, there is a diverse array of content that can be considered misinformation, such as fake news and satire. Similarly, in the field of deep learning, there are several architectures with variable efficacy depending on the context and data involved. This study aims to highlight the various types of misinformation attacks and deep learning architectures that are used to detect them. Based on our selection of the recent literature, we present a classification of deep learning approaches and their relative effectiveness in detecting misinformation, along with their limitations in terms of accuracy as well as computational overhead. Finally, we discuss some challenges and limitations that arise FROM the use of deep learning architectures in misinformation detection.
Published in: IT Professional ( Volume: 25, Issue: 5, Sept.-Oct. 2023)