SIFT Method

Evaluate Sources or AI Generated Content Claims Using

The SIFT method is an evaluation strategy developed by digital literacy expert, Mike Caulfield, to help determine whether online content can be trusted for credible or reliable sources of information. All SIFT information on this page is adapted from his materials with a CC BY 4.0 license.

From https://guides.lib.uchicago.edu/misinformation

Try to find the original study, source, or quote of information. In the case of Generative AI, the content could be a hallucination (false information generated by the AI tool).

Ask yourself: Was the claim, quote, or media fairly represented? Does the extracted information support the original claims in the research? ​ Is information being cherry-picked to support an agenda or a bias?​ Is information being taken out of context?

Trace Claims

Are you feeling strong emotions? Ask yourself why? You feelings might cloud your perspective.

Do you know and trust the website or Generative AI output as a source of information?

Don't read it or share it until you know what it is

If you feel yourself getting overwhelmed in your fact-checking efforts, STOP and take a second to remind yourself what your goal is.

STOP

Taking sixty seconds to figure out where it is from before reading will help you decide if it is worth your time, and if it is, help you to better understand its significance and trustworthiness.

Investigating the source does not require you to do in-depth research and analysis. Rather, this step is a quick check into the expertise and agenda of the online content in question.

This is where you start to answer the questions you asked yourself at STOP: What kind of content is this? Is it a blog post, article, or statistic? Who wrote it? Who is it published by?

Investigate the Source

Factcheck.org

Try a fact checker such as:

Use lateral reading (opening multiple tabs across your browser) to read more about the claim from other sources

Find other sources that corroborate or refute the information in the claim made by the source or Generative AI output

Find Trusted Coverage