We are proud to share that our research paper “Identifying Nuances in Fake News vs. Satire: Using Semantic and Linguistic Cues” has been accepted to the prestigious EMNLP conference. This work is part of our Research Program which aims to develop state-of-the-art Natural Language Processing and advance scientific knowledge on fighting misinformation. The topic of this work, differentiating between Fake News and Satire, carries great implications with regard to the delicate balance of fighting misinformation while protecting free speech.
We have been working on this project together with researches from Amazon AI and the George Washington University. The paper was presented in the NLP for Internet Freedom event on November 4th co-located with the 2019 Conference on Empirical Methods in Natural Language Processing.
Following are a few highlights of the paper
- The blurry line between nefarious fake news and protected-speech satire has been a notorious struggle for social media platforms. Further to the efforts of reducing exposure to misinformation on social media, purveyors of fake news have begun to masquerade as satire sites to avoid being demoted.
- In this work, we address the challenge of automatically classifying fake news versus satire. Contrary to fake news, satire stories are usually humorous and carry some political or social message. We hypothesize that these nuances could be identified using semantic and linguistic cues.
- We studied the feature importance of our method to help shed light on the nuances between fake news and satire. For instance, we observed that satire articles are more sophisticated, or less easy to read, than fake news articles.
- Overall, our contributions, with the improved classification accuracy and towards the understanding of nuances between fake news and satire, carry great implications with regard to the delicate balance of fighting misinformation while protecting free speech.
The full paper can be found on arXiv.org.
Please feel free to check out our GitHub repository for the reproducibility report including codes and results.
The paper was also covered by VentureBeat and ZDNet – read more here:
Researchers develop AI that distinguishes between satire and fake news
You must be logged in to post a comment.