Date of Award
Doctor of Philosophy (PhD)
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.
Prairie View A&M University
Rights© 2021 Prairie View A & M University
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Date of Digitization
John B Coleman Library
City of Publication
Kotteti, C. M. (2020). Fake News Detection in Social Media Using Machine Learning and Deep Learning. Retrieved from https://digitalcommons.pvamu.edu/pvamu-dissertations/4