The #FakeRankChallenge: Can AI Identify Fake News on Your Twitter Feed?
We live in an age where #Fakenews and #disinformation are becoming more and more common. With the #covid19pandemic and the upcoming #uselections2020 this phenomenon is on the rise. To try curb the spread of disinformation, AdVerifai is now releasing the #FakeRankChallenge. The app lets you scan your #twitter feed or twitter accounts of famous people and check if the #FakeRank #AI can detect any fake news. Read more and try it out here: http://fakerank.adverifai.com/
In this post we share more details about how the technology works and answer popular questions regarding AI bias, AI explainability and more.
How Does it work?
First, we get the tweets of a user including text and outgoing links.
Second, the tweets content is supplied to the FakeRank API and being analyzed to identify questionable content.
Third, the front-end interface collects the results from the API and presents the FakeRank score.
What is the FakeRank Sore?
The FakeRank score represents the probability of content to be safe or questionable based on our Machine Learning model — FakeRank. It is calculated using deep neural networks and unique psycho-linguistic cues that are able to capture the psychology and semantic meaning of text to automatically detect the various kinds of disinformation and hate speech.
Read more: Identifying Nuances in Fake News vs. Satire: Using Semantic and Linguistic Cues
What data is used to train the FakeRank?
Data is one of the most important elements of a machine learning task. It is especially challenging in this task, where quality labeled data is scarce and the and ground truth established by training algorithms on human work is neither universal nor permanent. Through our collaboration with fact checking partners, we are able to collect unique data which serves to build better models and attract more partners and more data.
Since models are only as good and unbiased as the data they use, the FakeRank AI is trained on data labeled by fact-checking organizations that comply with the IFCN code of principles of Nonpartisanship, Fairness and Transparency. Moreover, the FakeRank AI is not a black-box. We invested in developing explainable AI that provides a score, but more importantly, insights into the logic that resulted in that score
What are the different types of Fake News FakeRank can identify?
FakeRank distinguishes between 3 main categories of Fake News:
- Extreme political bias — Strongly biased language promoting far-right or far-left ideologies. May utilize strong loaded wording that attempts to influence an audience by using appeal to emotion or stereotypes
- Conspiracy — Theories based on unverifiable information or that is not supported by evidence. Examples include Illuminati, Aliens, Chemtrails and more
- Pseudo-science — Dubious health claims or theories mistakenly regarded as being based on scientific methods. Common topics include vaccination and climate change
Does the FakeRank judgement pretends to represent the absolute truth?
It’s important to emphasize that FakeRank is not aiming to be the source of truth. We do not provide judgement. We provide measurement. More specifically, we provide AI to empower humans to address the scale of the problem (as opposed to manual checking).
Any questions or ideas? Feel free to contact us Want to play? check out our API
