Fake news detection based on explicit and implicit signals of a hybrid crowd: An approach inspired in meta-learning

Freire, Paulo Márcio Souza; Silva, Flávio Roberto Matias da; Goldschmidt, Ronaldo R.

doi:10.1016/j.eswa.2021.115414

Cited by 27 publications

(10 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They utilized machine learning and deep learning techniques to train these features and predict the news as false or genuine. Freire et al [51] used crowd signals inspired by the meta information for detecting fake news. Raj and Meel [52] also utilized covNet for text and images but used the early fusion technique.…”

Section: Multi-modal Approachmentioning

confidence: 99%

FakedBits- Detecting Fake Information on Social Platforms using Multi-Modal Features

2023

KSII TIIS

View full text Add to dashboard Cite

Social media play a significant role in communicating information across the globe, connecting with loved ones, getting the news, communicating ideas, etc. However, a group of people uses social media to spread fake information, which has a bad impact on society. Therefore, minimizing fake news and its detection are the two primary challenges that need to be addressed. This paper presents a multi-modal deep learning technique to address the above challenges. The proposed modal can use and process visual and textual features. Therefore, it has the ability to detect fake information from visual and textual data. We used EfficientNet-B0 and a sentence transformer, respectively, for detecting counterfeit images and for textural learning. Feature embedding is performed at individual channels, whilst fusion is done at the last classification layer. The late fusion is applied intentionally to mitigate the noisy data that are generated by multi-modalities. Extensive experiments are conducted, and performance is evaluated against state-of-the-art methods. Three real-world benchmark datasets, such as MediaEval (Twitter), Weibo, and Fakeddit, are used for experimentation. Result reveals that the proposed modal outperformed the state-of-the-art methods and achieved an accuracy of 86.48%, 82.50%, and 88.80%, respectively, for MediaEval (Twitter), Weibo, and Fakeddit datasets.

show abstract

Section: Multi-modal Approachmentioning

confidence: 99%

FakedBits- Detecting Fake Information on Social Platforms using Multi-Modal Features

2023

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…Several survey and review papers that contain detection challenges and potential open issues have been published recently, including but not limited to [34][35][36][37][40][41][42][43]. Many issues have been researched related to feature extraction [6][7][8][9][10], representation [8,[11][12][13][14][15][16][17], classification [6,12,[18][19][20][21][22][23][24][25], and model design [10,16,21,22,[26][27][28][29][30][31][32]. Various solutions have been investigated using statical, traditional machine and deep learning and natural languageprocessing techniques.…”

Section: Related Workmentioning

confidence: 99%

“…Several approaches have been suggested to identify fake news. Numerous issues have been studied related to feature extraction [6][7][8][9][10], representation [8,[11][12][13][14][15][16][17], classification [6,12,[18][19][20][21][22][23][24][25], and model design [10,16,21,22,[26][27][28][29][30][31][32]. Based on the representative features that are employed, fake news detection techniques can be can be categorized into four groups: content-, knowledge-, users-, and propagation-based features.…”

Section: Introductionmentioning

confidence: 99%

Web-Informed-Augmented Fake News Detection Model Using Stacked Layers of Convolutional Neural Network and Deep Autoencoder

et al. 2023

View full text Add to dashboard Cite

Today, fake news is a growing concern due to its devastating impacts on communities. The rise of social media, which many users consider the main source of news, has exacerbated this issue because individuals can easily disseminate fake news more quickly and inexpensive with fewer checks and filters than traditional news media. Numerous approaches have been explored to automate the detection and prevent the spread of fake news. However, achieving accurate detection requires addressing two crucial aspects: obtaining the representative features of effective news and designing an appropriate model. Most of the existing solutions rely solely on content-based features that are insufficient and overlapping. Moreover, most of the models used for classification are constructed with the concept of a dense features vector unsuitable for short news sentences. To address this problem, this study proposed a Web-Informed-Augmented Fake News Detection Model using Stacked Layers of Convolutional Neural Network and Deep Autoencoder called ICNN-AEN-DM. The augmented information is gathered from web searches from trusted sources to either support or reject the claims in the news content. Then staked layers of CNN with a deep autoencoder were constructed to train a probabilistic deep learning-base classifier. The probabilistic outputs of the stacked layers were used to train decision-making by staking multilayer perceptron (MLP) layers to the probabilistic deep learning layers. The results based on extensive experiments challenging datasets show that the proposed model performs better than the related work models. It achieves 26.6% and 8% improvement in detection accuracy and overall detection performance, respectively. Such achievements are promising for reducing the negative impacts of fake news on communities.

show abstract

“…For different types of knowledge and ability points of higher vocational courses, based on the theories of pedagogy, cognitive science and psychology, the categories of meta-learning behaviors, possible combinations of meta-learning behaviors, and associated attributes of learning behaviors involved in different types of professional theoretical knowledge, the formation of professional skills, and the exploration and solution of professional problems are systematically analyzed. The possible sets of meta-learning behaviors for higher vocational professional course learning are extracted inductively [24]:…”

Section: Analysis Of the Elements Of Learning Behaviormentioning

confidence: 99%

Vocational Education and Industry Integration and Symbiosis of Subjects and Digital Drivers

Guo

2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

Under the new round of scientific and technological revolution and industrial change, the integration of vocational education and industry is an important direction of educational development. In this paper, the structure of the learning path network of higher vocational professional courses is analyzed, and through the analysis of the elements of learning behaviors, the learning behaviors are mined by adopting sequence relations, and the behavioral structure model is established. The assessment of the learning path under the integration of industry and education courses was finished using uncertainty association coefficients and time association coefficients. After building the learning path network for vocational education, the subjective characteristics of students under vocational education were detected using isolated point analysis. The detection results show that the correlation coefficient between the first pair of typical variables is 0.488. The Wilks statistical test results for typical correlation coefficients show that the p-value of the first typical correlation coefficient is 0.098, which is less than 10%. The correlation study of the environment of integration of education and industry and the effect of integration can be simplified to study only the relationship between the first pair of typical variables. By analyzing the main characteristics, the main body for vocational education and industry integration is clarified, which creates a digital-driven impetus for the integration of industry and education.

show abstract

Fake news detection based on explicit and implicit signals of a hybrid crowd: An approach inspired in meta-learning

Cited by 27 publications

References 51 publications

FakedBits- Detecting Fake Information on Social Platforms using Multi-Modal Features

FakedBits- Detecting Fake Information on Social Platforms using Multi-Modal Features

Web-Informed-Augmented Fake News Detection Model Using Stacked Layers of Convolutional Neural Network and Deep Autoencoder

Vocational Education and Industry Integration and Symbiosis of Subjects and Digital Drivers

Contact Info

Product

Resources

About