Arabic Rumor Detection Using Contextual Deep Bidirectional Language Modeling

Bahurmuz, Naelah O.; Amoudi, Ghada; Baothman, Fatmah; Jamal, Amani; Alghamdi, Hanan S.; Alhothali, Areej

doi:10.1109/access.2022.3217522

Cited by 8 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned, Transformers can work in parallel, allowing them to operate faster and on larger datasets. In this case, they manage to capture the temporal dependence of the data through additional vectors internally in their architecture Bahurmuz et al (2022). Figure 1 shows the general functioning of the Transformers architecture in more detail.…”

Section: Transformersmentioning

confidence: 99%

Transformers as a classifier for solar flare time series: a comparative study

Ferreira,

Gradvohl,

Silva

et al. 2024

Preprint

View full text Add to dashboard Cite

Solar flares are violent and sudden eruptions that occur in the solar atmosphere and release energy in the form of radiation. They can affect technological systems on Earth and in its orbit, causing financial losses and damage to human life. Therefore, it is necessary to predict the occurrence of such flares to mitigate their effects. Specialized instruments gather data for solar activity monitoring. Hence, we can create prediction models using machine learning from this data. From an analysis of the literature, we noticed the prevalence of some algorithms, such as Multi-layer Perceptrons (MLP), Support Vector Machines (SVM), and Long Short-Term Memory (LSTM), which presented good results, mainly considering the True Skill Statistic (TSS) metric. In parallel, in 2017, a new deep learning-based neural network architecture called Transformers emerged. Researchers initially created it for natural language processing. However, Transformers were successfully employed in other domains, such as time series forecasting. Solar activity data is considered a time series due to its continuous capture over time. Consequently, we can employ Transformers to develop a solar flare forecast model. Considering a significant lack of work using Transformers for solar flare forecasting, we ran experiments to test the Transformers' viability and performance in solar flare forecast models. We created models using other algorithms (MLP, SVM, LSTM, Transformers) to investigate the Transformers' performance and compared them using accuracy, TSS, and Area Under the ROC Curve (AUC) metrics. We observed that the Transformers had superior performance compared to the other models. For instance, the Transformers' TSS metric average was 0.9, contrasting the other models' TSS=0.4. The difference was slightly smaller in AUC, where Transformers reached 0.9, and the others reached no more than 0.7. Therefore, we can use the Transformers to classify solar flare data and obtain superior results compared to other models. We also conducted experiments using different forms of data balancing, including unbalanced data, balanced with undersampling, oversampling, and SMOTE techniques. The MLP, SVM, and LSTM models showed significant improvements in balance, where the average TSS increased from 0.1 to 0.4. On the other hand, Transformers were not sensitive to data balancing, presenting the most stable TSS in all cases.

show abstract

Section: Transformersmentioning

confidence: 99%

Transformers as a classifier for solar flare time series: a comparative study

Ferreira,

Gradvohl,

Silva

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…It holds the potential to deliver favorable results in terms of accuracy and performance. According to Alkhodair et al [37], this proposal leverages the long-short recurrent neural network, and efforts will be made to improve this model to achieve higher accuracy.…”

Section: Related Workmentioning

confidence: 99%

A Robust Rumor Detection on Twitter Using an Enhanced LSTM-RNN Model

Ma,

Luo,

Zheng

et al. 2024

Preprint

View full text Add to dashboard Cite

Social networks have significantly impacted people’s lifestyles, providing a crucial platform for communication and information sharing that can engage millions of users within seconds. While social media offers positive influences on lives and relationships, it also fosters the spread of rumors, resulting in adverse effects such as loss of reputation, credibility, and health. This paper introduces a novel algorithm based on long short-term memory and recurrent neural networks (LSTM-RNN) for detecting rumors on Twitter. The proposed algorithm’s performance is evaluated through extensive simulations using the AUG-RNR-DATA dataset, which includes both rumor and non-rumor tweets from six distinct events. The simulation results demonstrate that our algorithm surpasses the baseline methods, achieving a 0.95 accuracy in distinguishing between rumors and non-rumors on the AUG-RNR-DATA dataset.

show abstract

“…Taking into consideration the inconsistent information density and importance across different spatial regions in the images, the input images are subjected to block-wise feature extraction. Firstly, the VGG19 network pretrained on ImageNet [35] is fine-tuned using the dataset for false news classification tasks. For an input image I, a feature map of size 7×7×512 can be obtained from the last convolutional layer of the VGG19 network.…”

Section: Visual Semantic Encodermentioning

confidence: 99%

Deep Learning Based Semantic Model for Multimodal Fake News Detection

2024

IJIES

View full text Add to dashboard Cite

Social media has gradually become the primary news source for people in recent years, providing convenience but also leading to the spread of false information. With the rise of media-rich social media platforms, fake news has evolved from single-text to multimodal formats, prompting increased attention to multi-modal fake news detection. However, most existing methods rely on representation-level features that are closely tied to the dataset, resulting in insufficient modelling of semantic-level features and a limited ability to generalize to new data. To address this issue, we propose a semantically enhanced multimodal fake news detection method that utilizes pre-trained language models to capture implicit factual knowledge and explicitly extracts visual entities to better understand the deep semantics of multimodal news. We also extract visible features at different semantic levels, use a text-guided attention mechanism to model semantic interactions between text and images, and integrate multimodal features. Experimental results on real datasets based on Weibo news demonstrate that the proposed method outperforms other methods with an accuracy of 0.895 in multimodal fake news detection.

show abstract

Arabic Rumor Detection Using Contextual Deep Bidirectional Language Modeling

Cited by 8 publications

References 43 publications

Transformers as a classifier for solar flare time series: a comparative study

Transformers as a classifier for solar flare time series: a comparative study

A Robust Rumor Detection on Twitter Using an Enhanced LSTM-RNN Model

Deep Learning Based Semantic Model for Multimodal Fake News Detection

Contact Info

Product

Resources

About