Attention:The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Thursday, October 15th until 12:00 AM ET on Friday, October 16th due to maintenance. We apologize for the inconvenience.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Machine Learning-Based Identifications of COVID-19 Fake News Using Biomedical Information Extraction
The spread of fake news related to COVID-19 is an infodemic that leads to a public health crisis. Therefore, detecting fake news is crucial for an effective management of the COVID-19 pandemic response. Studies have shown that machine learning models can detect COVID-19 fake news based on the content of news articles. However, the use of biomedical information, which is often featured in COVID-19 news, has not been explored in the development of these models. We present a novel approach for predicting COVID-19 fake news by leveraging biomedical information extraction (BioIE) in combination with machine learning models. We analyzed 1164 COVID-19 news articles and used advanced BioIE algorithms to extract 158 novel features. These features were then used to train 15 machine learning classifiers to predict COVID-19 fake news. Among the 15 classifiers, the random forest model achieved the best performance with an area under the ROC curve (AUC) of 0.882, which is 12.36% to 31.05% higher compared to models trained on traditional features. Furthermore, incorporating BioIE-based features improved the performance of a state-of-the-art multi-modality model (AUC 0.914 vs. 0.887). Our study suggests that incorporating biomedical information into fake news detection models improves their performance, and thus could be a valuable tool in the fight against the COVID-19 infodemic.  more » « less
Award ID(s):
1742517
PAR ID:
10484386
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
MPDI
Date Published:
Journal Name:
Big Data and Cognitive Computing
Volume:
7
Issue:
1
ISSN:
2504-2289
Page Range / eLocation ID:
46
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, 2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech))
    Raw datasets collected for fake news detection usually contain some noise such as missing values. In order to improve the performance of machine learning based fake news detection, a novel data preprocessing method is proposed in this paper to process the missing values. Specifically, we have successfully handled the missing values problem by using data imputation for both categorical and numerical features. For categorical features, we imputed missing values with the most frequent value in the columns. For numerical features, the mean value of the column is used to impute numerical missing values. In addition, TF-IDF vectorization is applied in feature extraction to filter out irrelevant features. Experimental results show that Multi-Layer Perceptron (MLP) classifier with the proposed data preprocessing method outperforms baselines and improves the prediction accuracy by more than 15%. 
    more » « less
  2. ; ; ; (, Proceedings of the ACM on Human-Computer Interaction)
    Social media have become essential in daily life, serving as platforms for public opinion, personal growth, and news consumption. This shift in how people access news has led to an increase in misinformation, including fake news intended to deceive. Various psychological and social factors, such as emotional appeal, cognitive biases, and social influence, drive individuals' susceptibility to believing false information. While prior studies have examined the believability of news content, large-scale analyses on real social media platforms remain limited, as well as studying factors influencing the believability of real and fake news separately and analyzing similarities and differences. This study introduces a new dataset of 14,535 Twitter user comments, annotated to measure user believability in real versus fake news. Using this dataset, we address the problem of predicting news believability and study which user or news characteristics predict believability in real and fake news, as well as checking whether believability enhances fake news detection. We employ machine learning models incorporating news style, emotional content, and user traits to predict believability and apply explainability methods to clarify key characteristics influencing user belief. Overall, the models achieved significant results in detecting news believability and several news and user-based features such as writing style, emotion, personality, and psychology have been individuated as strong predictors of believability in news. We further integrate believability insights into advanced fake news detectors, demonstrating improved performance. To our knowledge, this is the first large-scale human-annotated English dataset designed for studying news believability, which we have released for use in future research. 
    more » « less
  3. ; ; ; ; ; ; (, Proceedings of the AAAI Conference on Artificial Intelligence)
    null (Ed.)
    Today social media has become the primary source for news. Via social media platforms, fake news travel at unprecedented speeds, reach global audiences and put users and communities at great risk. Therefore, it is extremely important to detect fake news as early as possible. Recently, deep learning based approaches have shown improved performance in fake news detection. However, the training of such models requires a large amount of labeled data, but manual annotation is time-consuming and expensive. Moreover, due to the dynamic nature of news, annotated samples may become outdated quickly and cannot represent the news articles on newly emerged events. Therefore, how to obtain fresh and high-quality labeled samples is the major challenge in employing deep learning models for fake news detection. In order to tackle this challenge, we propose a reinforced weakly-supervised fake news detection framework, i.e., WeFEND, which can leverage users' reports as weak supervision to enlarge the amount of training data for fake news detection. The proposed framework consists of three main components: the annotator, the reinforced selector and the fake news detector. The annotator can automatically assign weak labels for unlabeled news based on users' reports. The reinforced selector using reinforcement learning techniques chooses high-quality samples from the weakly labeled data and filters out those low-quality ones that may degrade the detector's prediction performance. The fake news detector aims to identify fake news based on the news content. We tested the proposed framework on a large collection of news articles published via WeChat official accounts and associated user reports. Extensive experiments on this dataset show that the proposed WeFEND model achieves the best performance compared with the state-of-the-art methods. 
    more » « less
  4. ; ; ; ; ; ; (, Frontiers in Communication)
    null (Ed.)
    In times of uncertainty, people often seek out information to help alleviate fear, possibly leaving them vulnerable to false information. During the COVID-19 pandemic, we attended to a viral spread of incorrect and misleading information that compromised collective actions and public health measures to contain the spread of the disease. We investigated the influence of fear of COVID-19 on social and cognitive factors including believing in fake news, bullshit receptivity, overclaiming, and problem-solving—within two of the populations that have been severely hit by COVID-19: Italy and the United States of America. To gain a better understanding of the role of misinformation during the early height of the COVID-19 pandemic, we also investigated whether problem-solving ability and socio-cognitive polarization were associated with believing in fake news. Results showed that fear of COVID-19 is related to seeking out information about the virus and avoiding infection in the Italian and American samples, as well as a willingness to share real news (COVID and non-COVID-related) headlines in the American sample. However, fear positively correlated with bullshit receptivity, suggesting that the pandemic might have contributed to creating a situation where people were pushed toward pseudo-profound existential beliefs. Furthermore, problem-solving ability was associated with correctly discerning real or fake news, whereas socio-cognitive polarization was the strongest predictor of believing in fake news in both samples. From these results, we concluded that a construct reflecting cognitive rigidity, neglecting alternative information, and black-and-white thinking negatively predicts the ability to discern fake from real news. Such a construct extends also to reasoning processes based on thinking outside the box and considering alternative information such as problem-solving. 
    more » « less
  5. ; ; (, ACM SIGKDD Explorations Newsletter)
    The threat that online fake news and misinformation pose to democracy, justice, public confidence, and especially to vulnerable populations has led to a sharp increase in the need for fake news detection and intervention. Whether multi-modal or pure text-based, most existing fake news detection methods depend on textual analysis of entire articles. However, these fake news detection methods come with certain limitations. For instance, fake news detection methods that rely on full text can be computationally inefficient, demand large amounts of training data to achieve competitive accuracy, and may lack robustness across different datasets. This is because fake news datasets have strong variations in terms of the level and types of information they provide; where some can include large paragraphs of text with images and metadata, and others can be a few short sentences. Perhaps if one could only use minimal information to detect fake news, fake news detection methods could become more robust and resilient to the lack of information. We aim to overcome these limitations by detecting fake news using systematically selected, limited information that is both effective and capable of delivering robust, promising performance. We propose a framework called SLIM (Systematically-selected Limited Information) for fake news detection. In SLIM, we quantify the amount of information by introducing information-theoretic measures. SLIM leverages limited information (e.g., a few named entities) to achieve performance in fake news detection comparable to that of state-of-the-art obtained using the full text, even when the dataset is sparse. Furthermore, by combining various types of limited information, SLIM can perform even better while significantly reducing the quantity of information required for training compared to state-of-the-art language model-based fake news detection techniques. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Text Encoded Conversion
  • XML
  • Save / Share this Record
  • Send to Email