Date of Award

8-2020

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Electrical Engineering

Abstract

Fake news detection in social media is a process of detecting false information that is intentionally created to mislead readers. The spread of fake news may cause social, economic, and political turmoil if their proliferation is not prevented. However, fake news detection using machine learning faces many challenges. Datasets of fake news are usually unstructured and noisy. Fake news often mimics true news. In this study, a data preprocessing method is proposed for mitigating missing values in the datasets to enhance fake news detection accuracy. The experimental results show that Multi- Layer Perceptron (MLP) classifier combined with the proposed data preprocessing method outperforms the state-of-the-art methods.

Furthermore, to improve the early detection of rumors in social media, a time-series model is proposed for fake news detection in social media using Twitter data. With the proposed model, computational complexity has been reduced significantly in terms of machine learning models training and testing times while achieving similar results as state-of-the-art in the literature. Besides, the proposed method has a simplified feature extraction process, because only the temporal features of the Twitter data are used. Moreover, deep learning techniques are also applied to fake news detection. Experimental results demonstrate that deep learning methods outperformed traditional machine learning models. Specifically, the ensemble-based deep learning classification model achieved top performance.

Committee Chair/Advisor

Lijun Qian

Committee Member

Kelvin Kirby

Committee Member

Xiangfang Li

Committee Member

Xishuang Dong

Committee Member

Na Li

Publisher

Prairie View A&M University

Rights

© 2021 Prairie View A & M University

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Date of Digitization

4-13-2022

Contributing Institution

John B Coleman Library

City of Publication

Prairie View

MIME Type

Application/PDF

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.