This Is AuburnElectronic Theses and Dissertations

Fake News Detection with Quantum Machine Learning




Tian, Ziyan

Type of Degree

PhD Dissertation


Computer Science and Software Engineering

Restriction Status


Restriction Type


Date Available



Social media has become a popular platform as a source of news or information in mod- ern life as a result of its timeliness and convenience, but it raises several critical issues. The leading issue is the spread of fake news on social media. Fake news has been considered a threat to democracy and the credibility of information. Detecting fake news is a more complex problem when compared to other online malicious behaviors. Several studies have proven that machine learning can be effectively leveraged as a solution for fake news detec- tion. However, with the increasing amount of data, traditional machine learning algorithms will face challenges with ingesting and processing large amounts of data. Quantum machine learning can be a viable solution. Quantum machine learning can be leveraged to address this issue. Research has proven that quantum computing can be utilized to solve computa- tionally intensive problems, and quantum algorithms can achieve an exponential or quadratic speed-up for solving the same problems. To explore the application of quantum machine learning techniques within the field of fake news detection, this research leverages the quantum K-Nearest Neighbors (KNN) model, the Quantum Support Vector Machine (QSVM) model, and the Variational Quantum Classifier (VQC). The experiments and results in this research suggest that it is possible to utilize quantum machine learning to effectively address the problem of fake news detection.