Predict Your FOIA Request Success

Source:, 2017

Does your FOIA have a shot? This model is trained on 9,000+ FOIA requests tracked by MuckRock.

Predictions made using a K nearest neighbors classification algorithm with a test classification accuracy rate of 80%. Factors include word count, average sentence length, specificity (presence of nouns), references to fees, references to FOIA, presence of hyperlinks, presence of email addresses, and success rate of agency.
What makes a good FOIA request? We studied 33,000 to find out.
Source: Nicolas Dias, Rashida Kamal, and Laurent Bastien, January 30, 2017

Every journalist has ideas about what makes a good public records request. But surprisingly few people have actually tried to systematically analyze how requests can be written to improve their chances of success. To fill this vacuum, we analyzed more than 33,000 Freedom of Information Act requests and identified a few characteristics that were typical of those that were fulfilled…..