Loading...

Fake News Spreading Mitigation Via Tracing Information In Social Networks

Rafiei, Mina | 2019

1854 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 52446 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Rabiee, Hamid Reza
  7. Abstract:
  8. Expansion of using social networks for reading and sharing news on the one hand, allows for quick and easy access to the news, but on the other hand, increases the spread of fake news and misleads many users. Therefore, identifying the fake news and attempting to mitigate its spreading on social networks is one of the major research areas in recent years. An important issue in this regard is reducing the time gap between news release time and identifying it as fake and starting to take action. Many researches has been done on detection of fake news, but since there is a trade-off between minimizing the time gap and maximizing accuracy, work on these models continues. There are also different model to deal with fake news mitigation. The point of most of these works is that they use a graph of user relationships as if extracting this graph is time-consuming and not available in most of the fake news data sets.In this study, we focus on accurate early labeling of news, and propose a model by considering earliness both in modeling and prediction. The proposed model tries to utilize a deep neural network architecture along with the use of structural features and linguistic and user sequence features, all of which are easily accessible, for each news sequence to specify the optimal point to identify the news label. Also, we propose a model for fake news mitigation based on deep neural networks that uses the same available sequence information. model can predict potential users in news future sequence to send them real news and prevent more propagation of fake news.The results of the proposed models are evaluated on the real world datasets. In the fake news detection model, although the model uses a shorter sequence than the other models, it offers better accuracy in most datasets. In the mitigation model, since the previous models did not use this input to mitigate the fake news, it is not possible to compare the work to them but comparing model to other sequence prediction models, our model achieves better results
  9. Keywords:
  10. Social Networks ; Fake News Detection ; Fake News Mitigation ; Deep Neural Networks

 Digital Object List

 Bookmark

...see more