Teaching students to distinguish between trustworthy and untrustworthy sources of news has taken on an increased urgency, and the Chronicle of Higher Education recently described this as a higher education trend for 2017. Are there any freely available datasets on this issue that are amenable to the pedagogy of statistics?

In particular, I am looking for any dataset on trustworthy versus untrustworthy news sources, or on related issues, such as how the use of different media sources is associated with how well informed a person is. My goal is to integrate one or more datasets into undergraduate statistics courses in psychology, one course for 2nd year students and the other for 4th year. I'm certainly willing to simplify the data for teaching purposes if necessary.

  • In the past I have seen a list of the most-cited websites in Wikipedia. Being cited a lot in Wikipedia is probably an indication of rather high trustworthiness. I can't find that list anymore, unfortunately. You might want to ask on the talk page of en.wikipedia.org/wiki/Wikipedia:Reliable_sources_checklist Similarly, Wikipedia has a list of websites that are banned from being linked to, but I am not sure it is public.
    – Nicolas Raoul
    Mar 1, 2017 at 7:24

1 Answer 1


There is a Pew Research study from July, 2016 on Trust and Accuracy of news media


Few have a lot of confidence in the information they get from professional outlets or friends and family, but large majorities have at least some trust in both; social media gets substantially lower trust scores.

Dataset (requires email registration) - http://www.journalism.org/dataset/american-trends-panel-wave-14-5/

Use Policy - http://www.pewresearch.org/about/use-policy/

All Pew Research datasets


enter image description here

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.