Abstract

The internet and the high use of social media have enabled the modern-day journalism to publish, share and spread news that is difficult to distinguish if it is true or fake. Defining “fake news” is not well established yet, however, it can be categorized under several labels: false, biased, or framed to mislead the readers that are characterized as propaganda. Digital content production technologies with logical fallacies and emotional language can be used as propaganda techniques to gain more readers or mislead the audience. Recently, several researchers have proposed deep learning (DL) models to address this issue. This research paper provides an ensemble deep learning model using BiLSTM, XGBoost, and BERT to detect propaganda. The proposed model has been applied on the dataset provided by the challenge NLP4IF 2019, Task 1 Sentence Level Classification (SLC) and it shows a significant performance over the baseline model.

Highlights

  • The spread of news has been transformed from traditional news distributors to social media feeds

  • Knowing that deep learning is outperforming traditional machine learning techniques, we have proposed an ensemble deep learning model using Bidirectional Long Short-Term Memory (BiLSTM), XGBoost, and Bidirectional Encoder Representations from Transformers (BERT) to address this challenge

  • One of the key findings is noticing that BERT model gives better prediction than the other models, which indicates that BERT can understand the text better than the other models

Read more

Summary

Introduction

The spread of news has been transformed from traditional news distributors to social media feeds. Identifying an article as fake news relies on the degree of falsity and intentionality of spreading the news. News with propaganda are called Propagandistic news articles, that are intentionally spread to mislead readers and influence their minds with a certain idea, for political, ideological, or business motivations (Tandoc Jr et al, 2018; Brennen, 2017). The key novelty of our work is using word embeddings and a unique set of semantic features, in a fully connected neural network architecture to determine the existence of propagandistic news in the article.

Related Work
Dataset and Extracted Features
Features
Our Approach
BiLSTM
XGBoost
Results and Evaluation
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.