Fake News Detection: An Application of Quantum K-Nearest Neighbors

Abstract

Social media has been a popular source for receiving news or information in daily life due to its rapid dissemination and ease of access. However, this trend causes a series of critical issues. The most critical issue, fake news, is a quickly growing threat. Fake news has the capability to compromise the democracy and credibility of information. Compared to other malicious threats, fake news is harder to detect due to being created to intentionally deceive target audiences. Various studies have been conducted and suggested that machine learning can be effectively utilized in detecting fake news. However, with the increasing amount of data, traditional machine learning algorithms will face challenges in ingesting and processing the data at scale. Thus, we propose a fake news detection system that incorporates both a quantum k-nearest neighbors (QKNN) machine learning model and Genetic and Evolutionary Feature Selection (GEFeS). With our proposed system, the highest accuracy achieved in this research is 87.12%.