🔒 Is it possible to create a fake or true news detection purely using language and vocabulary tests

[jolly mesa]

I lately created a model to predict whether a news article is fake or not based on the title and the text. it uses asssisted learning with tfidfvectorizer and decision trees with a moderately sized dataset to create a prediction engine. This was an exercise suggested by 365datascience but im wondering if that's really possible ?

project code for reference https://github.com/PhrogOfTheDay/FakeNewsDetection

[midnight scarab]

@jolly mesa

Python help channel opened

Remember to:

• Ask your Python question, not if you can ask or if there's an expert who can help.
• Show a code sample as text (rather than a screenshot) and the error message, if you've got one.
• Explain what you expect to happen and what actually happens.

:warning: Do not pip install anything that isn't related to your question, especially if asked to over DMs.

Closes after a period of inactivity, or when you send !close.

[hallow sphinx]

no
imagine this hypothetical article:

Title: Weather Today
Content: It's rainy today

[jolly mesa]

yeah got your point

[marble sphinx]

no

there are a lot of ways a "news" can be faked

so you need LLM+RAG

and you have to see that your LLM wont hallucinate

sklearn decision trees + others. are not for solving general purpose problems

[midnight scarab]

Python help channel closed

This help channel has been closed and it's no longer possible to send messages here. If your question wasn't answered, feel free to create a new post in #1035199133436354600. To maximize your chances of getting a response, check out this guide on asking good questions.