Using Deep Learning to Detect Rumors in Twitter

Providel, Eliana; Mendoza, Marcelo

doi:10.1007/978-3-030-49570-1_22

Cited by 10 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comparison study of deep learning rumor detection algorithms was conducted in [14], in which the performances of ten different deep learning architectures, including LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), were analysed based on two text encoding schemes: word2vec and BERT (Bidirectional Encoder Representations from Transformers). The results show that some architectures are more suitable for some particular datasets, suggesting that the use of a combination of different models would offer advantages in terms of the detection performance.…”

Section: Related Workmentioning

confidence: 99%

Rumor Detection Based on SAGNN: Simplified Aggregation Graph Neural Networks

Zhang

Li²,

Zhou

et al. 2021

MAKE

View full text Add to dashboard Cite

Identifying fake news on media has been an important issue. This is especially true considering the wide spread of rumors on popular social networks such as Twitter. Various kinds of techniques have been proposed for automatic rumor detection. In this work, we study the application of graph neural networks for rumor classification at a lower level, instead of applying existing neural network architectures to detect rumors. The responses to true rumors and false rumors display distinct characteristics. This suggests that it is essential to capture such interactions in an effective manner for a deep learning network to achieve better rumor detection performance. To this end we present a simplified aggregation graph neural network architecture. Experiments on publicly available Twitter datasets demonstrate that the proposed network has performance on a par with or even better than that of state-of-the-art graph convolutional networks, while significantly reducing the computational complexity.

show abstract

Section: Related Workmentioning

confidence: 99%

Rumor Detection Based on SAGNN: Simplified Aggregation Graph Neural Networks

Zhang

Li²,

Zhou

et al. 2021

MAKE

View full text Add to dashboard Cite

show abstract

“…The study by [12][13][14][15][16] highlighted the phased problems of the creation, propagation, and detection of false information but also concentrated on machine learning techniques while mostly disregarding deep learning techniques. Overall, published surveys primarily use machine learning techniques and only include a small number of deep learning techniques, which served as the inspiration for our work.…”

Section: Introductionmentioning

confidence: 99%

An Efficient CNN-based LSTM Approach to Detect the Rumor Prediction in COVID-19 Data using Fuzzy based Deep learning

Mukiri

Burra

2023

Preprint

View full text Add to dashboard Cite

As the traditional rumor detection method is concerned, reduce in the data accuracy may influence the observation directivity and lack in the extraction of feature datasets. In order to overcome the above problem, here the modified rumor prediction model is proposed using deep learning with the integration of CNN in order to improve the data accuracy with the help of neural networks. First, the continuous bag of words (CBOW) model is modified to define the window context based on the definition of the weighted module. Then, CNN gets modified with the association of the attention module added along with the output of the weighted module as it helps to identify the feature incompleteness in the long sequence of online social networks. The attention module along with CNN with the function of max pooling and upsampling layer in order to extract the features in the text effectively. Then, the extracted feature is given into the softmax layer for performing text classification to identify and predict the rumor in the online social network. Based on the online samples, the analysis is conducted on the proposed model based on certain parameter such as, data accuracy, precision, recall and F1-Score as it shows better performance as compared to the other existing models like LSTM based Fuzzy deep learning, deep recurrent Q-learning and adaptive deep transfer learning.

show abstract

“…After the emergence of deep learning technology, with its advantages in processing large-scale data, various neural network models have been successfully applied to solve different problems of rumor detection, such as the difficulty of quick rumor detection, the sparseness of early rumor data, and the dynamic nature of rumor information. Among the rumor detection models based on neural networks, those using graph neural networks can fully consider the graph structure information constructed in the process of rumor propagation, so they can get great classification results Providel and Mendoza (2020).…”

Section: Introductionmentioning

confidence: 99%

Federated Graph Attention Network for Rumor Detection

Wang¹,

Bai²,

Yao³

2022

Preprint

View full text Add to dashboard Cite

With the development of network technology, many social media are flourishing. Due to imperfect Internet regulation, the spread of false rumors has become a common problem on those social platforms. Social platforms can generate rumor data in their operation process, but existing rumor detection models are all constructed for a single social platform, which ignores the value of cross-platform rumor. This paper combines the federated learning paradigm with the bidirectional graph attention network rumor detection model and proposes the federated graph attention network(FedGAT) model for rumor detection. Taking the advantages of horizontal federated learning for cross-platform rumor detection, the security of each social platform's data information can be ensured. We construct both the server-side and client-side models as a bidirectional graph attention network rumor detection model in the federated learning paradigm framework. The local model on the client-side can train and verify the rumor data of the social platform in the iterative process, while the model on the server-side only plays the role of aggregating the characteristics of different social platform models and does not participate in the training of the model. Finally, we

show abstract

Using Deep Learning to Detect Rumors in Twitter

Cited by 10 publications

References 19 publications

Rumor Detection Based on SAGNN: Simplified Aggregation Graph Neural Networks

Rumor Detection Based on SAGNN: Simplified Aggregation Graph Neural Networks

An Efficient CNN-based LSTM Approach to Detect the Rumor Prediction in COVID-19 Data using Fuzzy based Deep learning

Federated Graph Attention Network for Rumor Detection

Contact Info

Product

Resources

About