Researchers built a method to spot the spread of propaganda for market manipulation
Over the last few years, established news outlets have been the subject of political and medical propaganda.
Most notably, China, Iran, and the United States are all three culprits in the spread of medical propaganda surrounding the origins of the COVID-19 pandemic, before any intergovernmental organization conducted a probe on the matter.
But the spread of propaganda is not just confined to politics and public health. In a recent study, released in the Journal of the Association for Information Systems, the problem of false stories in the media is also taking a toll on market manipulation.
As highlighted by researchers at the University of Göttingen, the spread of propaganda for manipulation in the stock market is an all-too-common practice. The research team developed a robust method of spotting such propaganda.
“We address the challenge of building an automated fraud detection system with robust classifiers that mitigate countermeasures from fraudsters in the field of information-based securities fraud,” their findings state. “Our work involves developing design principles for robust fraud detection systems and presenting corresponding design features.”
“The results indicate that the use of theory-based linguistic features and ensemble learning can significantly increase the robustness of classifiers and contribute to the effectiveness of robust fraud detection. We discuss implications for supervisory authorities, industry, and individual users,” researchers stated in their findings.
Given its purported effectiveness at spotting propaganda, the new method may be utilized for market surveillance and to help investors refrain from fraudulent schemes, providing new hope in the field of information-based securities fraud.
The study was authored by Michael Siering, Jan Muntermann, and Miha Grčar.