Fake News Classification Based on Content Level Features

Abstract

Due to the openness and easy accessibility of online social media (OSM), anyone can easily contribute a simple paragraph of text to express their opinion on an article that they have seen. Without access control mechanisms, it has been reported that there are many suspicious messages and accounts spreading across multiple platforms. Accordingly, identifying and labeling fake news is a demanding problem due to the massive amount of heterogeneous content. In essence, the functions of machine learning (ML) and natural language processing (NLP) are to enhance, speed up, and automate the analytical process. Therefore, this unstructured text can be transformed into meaningful data and insights. In this paper, the combination of ML and NLP are implemented to classify fake news based on an open, large and labeled corpus on Twitter. In this case, we compare several state-of-the-art ML and neural network models based on content-only features. To enhance classification performance, before the training process, the term frequency-inverse document frequency (TF-IDF) features were applied in ML training, while word embedding was utilized in neural network training. By implementing ML and NLP methods, all the traditional models have greater than 85% accuracy. All the neural network models have greater than 90% accuracy. From the experiments, we found that the neural network models outperform the traditional ML models by, on average, approximately 6% precision, with all neural network models reaching up to 90% accuracy.

A Comparative Study of Hybrid Machine Learning Approaches for Fake News Detection that Combine Multi-Stage Ensemble Learning and NLP-based Framework

“…By combining the usage of ML and NLP on a sizable and labeled corpus provided by Twitter, Chun-Ming Lai, Mei-Hua Chen, Endah Kristiani, Vinod Kumar Verma, and Chao-Tung Yang attempted to categorize the news data in another work. The conventional ML algorithms' accuracy was 85% and more than 90% with neural networks [21]. Abdulaziz Albahr and Marwan Albahr used the well-known "LIAR" dataset to create a model for detecting fake news.…”

AugFake-BERT: Handling Imbalance through Augmentation of Fake News Using BERT to Enhance the Performance of Fake News Classification

“…It is critical to pick the proper feature reduction algorithm, as feature reduction has a significant impact on text classification performance [36]. For this reason, traditional machine learning-based methods perform poorly on high-dimensional features [37]. For the most part, neural network-based approaches have performed better than traditional machine learning-based methods, as they reduce the curse of dimensionality.…”

Comparing SVM and Naïve Bayes Classifier for Fake News Detection

“…Extracting news article text features and processing them through a model consisting of machine learning and natural language processing (Jain et al, 2019). (Lai et al, 2022) used word vectorization to convert words into numeric values to be understood by their neural network model. The result of the models made can always be improved with many more methods and techniques (Aldwairi & Alwahedi, 2018;ArunKumar et al, 2020;Farokhian et al, 2022;Humayoun, 2022) helping to improvise the accuracy of information appearing on the internet.…”