Explainable Machine Learning for Fake News Detection

Reis, Júlio C. S.; Correia, A. Gomes; Murai, Fabrício; Veloso, Adriano; Benevenuto, Fabrí­cio

doi:10.1145/3292522.3326027

Cited by 81 publications

(36 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the feature-based approach (e.g., SHAP), each feature is characterized by an importance value for a particular prediction [12]. For example, Reis et al [35] examined a large and diverse set of features of fake news and found some features were very effective to detect certain types of fake news, which were used to explain model decisions to help detect fake news. The feature-based approach can provide two major advantages, including global and local interpretability.…”

Section: Related Workmentioning

confidence: 99%

Combat COVID-19 infodemic using explainable natural language processing models

Ayoub

Yang

Zhou

2021

Information Processing & Management

104

View full text Add to dashboard Cite

Misinformation of COVID-19 is prevalent on social media as the pandemic unfolds, and the associated risks are extremely high. Thus, it is critical to detect and combat such misinformation. Recently, deep learning models using natural language processing techniques, such as BERT (Bidirectional Encoder Representations from Transformers), have achieved great successes in detecting misinformation. In this paper, we proposed an explainable natural language processing model based on DistilBERT and SHAP (Shapley Additive exPlanations) to combat misinformation about COVID-19 due to their efficiency and effectiveness. First, we collected a dataset of 984 claims about COVID-19 with fact checking. By augmenting the data using back-translation, we doubled the sample size of the dataset and the DistilBERT model was able to obtain good performance

show abstract

Section: Related Workmentioning

confidence: 99%

Combat COVID-19 infodemic using explainable natural language processing models

Ayoub

Yang

Zhou

2021

Information Processing & Management

104

View full text Add to dashboard Cite

show abstract

“…Previous studies [19]- [21] have applied active learning to different applications. For example, authors in [19] presented a human-machine collaborative model to detect misleading information in social content.…”

Section: Figure 1 Overview Of the Proposed Methodsmentioning

confidence: 99%

“…The proposed model [20] initially creates a view-dependent classifier from a small labeled data and then applies active learning to enhance the model performance with additional annotated examples. Moreover, another system is presented in [21] to classify fake news by randomly selecting different sets of features to create a huge number of unbiased models; then, these models are ranked to define the best outcomes. However, although active learning has been applied to a wide range of applications, none of these approaches has tried to examine the problem of predicting the popularity of social news.…”

Section: Figure 1 Overview Of the Proposed Methodsmentioning

confidence: 99%

Improving News Popularity Estimation via Weak Supervision and Meta-active Learning

Nashaat¹,

Miller²

2021

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Social news has fundamentally changed the mechanisms of public perception, education, and even dis-information. Apprising the popularity of social news articles can have significant impact through a diversity of information redistribution techniques. In this article, an improved prediction algorithm is proposed to predict the long-time popularity of social news articles without the need for ground-truth observations. The proposed framework applies a novel active learning selection policy to obtain the optimal volume of observations and achieve superior predictive performance. To assess the proposed framework, a large set of experiments are undertaken; these indicate that the new solution can improve prediction performance by 28% (precision) while reducing the volume of required ground truth by 32%.

show abstract

“…The main results of this thesis appear in the following publications: [Reis et al 2020b, Reis et al 2019b, Reis et al 2019a, Reis et al 2017] and [Reis et al 2016] best paper honorable mention. Further, this thesis opens a novel dataset to the research community containing fact-checked fake images shared through WhatsApp during the 2018 Brazilian presidential election [Reis et al 2020a], as aforementioned.…”

Section: Academical and Social Impactsmentioning

confidence: 96%

Towards Automatic Fake News Detection in Digital Platforms: Properties, Limitations, and Applications

Reis¹,

Benevenuto²

2021

Anais Do XXXIV Concurso De Teses E Dissertações Da SBC (CTD-SBC 2021)

Self Cite

View full text Add to dashboard Cite

Digital platforms, including social media systems and messaging applications, have become a place for campaigns of misinformation that affect the credibility of the entire news ecosystem. The emergence of fake news in these environments has quickly evolved into a worldwide phenomenon, where the lack of scalable fact-checking strategies is especially worrisome. In this context, this thesis aim at investigating practical approaches for the automatic detection of fake news disseminated in digital platforms. Particularly, we explore new datasets and features for fake news detection to assess the prediction performance of current supervised machine learning approaches. We also propose an unbiased framework for quantifying the informativeness of features for fake news detection, and present an explanation of factors contributing to model decisions considering data from different scenarios. Finally, we propose and implement a new mechanism that accounts for the potential occurrence of fake news within the data, significantly reducing the number of content pieces journalists and fact-checkers have to go through before finding a fake story.

show abstract

Explainable Machine Learning for Fake News Detection

Cited by 81 publications

References 28 publications

Combat COVID-19 infodemic using explainable natural language processing models

Combat COVID-19 infodemic using explainable natural language processing models

Improving News Popularity Estimation via Weak Supervision and Meta-active Learning

Towards Automatic Fake News Detection in Digital Platforms: Properties, Limitations, and Applications

Contact Info

Product

Resources

About