Not a member? Sign up

AP's Overview tool helps DocumentCloud makes sense of text documents

by: Amy Gahran |

When you're tracking a story that involves reading a huge volume of text documents, it's a challenge to both manage and process the documents and see the big picture. Here's how two pieces of software can help.

A recent Knight Blog post explained how Associated Press reporter Jack Gillum used Document Cloud and Overview to show that showing that former Republican Vice Presidential Candidate Congressman Paul Ryan had requested funds for his district from many federal programs which he criticized on the campaign trail as wasteful.

According to Knight, Gillum relied on two tools to tackle this daunting task:

  • DocumentCloud, to upload scans of documents, perform optical character recognition, and search the contents.
  • Overview, a data visualization tool created by AP that expands the functionality of DocumentCloud to automatically sort documents into topics and visualize the contents.

Overview is designed primarily to process English-language text documents. It's not the tool to use to process tables, data that's primarily numeric, or records exported from a database (unless they include a field containing plain English text).

Both of these tools are available as web applications available for journalists to use free of charge. Both are also previous Knight News Challenge winners. You need a DocumentCloud account to use Overview.

Subscribe to the Newsletter

Amy Gahran

Amy Gahran is a journalist, editor, trainer, entrepreneur, strategist, and media consultant based in Boulder, Colorado. In addition to writing
Read More

Submit an event

Women's Hackathon October 9-11 in Los Angeles

October 9, 2015 - October 11, 2015

Register now for the Women’s Hackathon, devoted entirely to female students, faculty and professionals. The event will be held at the USC Annenberg School for Communication and Journalism in Los Angeles which is co-hosting the hackathon with MediaShift.

3-D: Digital, Diversity, Disruption: theme of ASNE-APME conference October 16-18

October 16, 2015 - October 18, 2015

The nation's top editors gather at the ASNE-APME annual conference October 16-18 in Silicon Valley at Stanford University in Palo Alto, CA.  The Associated Press Photo Managers is also a conference partner. 

Sales & Revenue Bootcamp for news organizations, October 19-20

Mon, October 19, 2015 9:00 am - Tue, October 20, 2015 5:00 pm

Learn sales and marketing skills to make your news site financially sustainable.  Apply for bootcamp, to be held at the Center for Cooperative Media at Montclair State University October 19-20,

Submit an event

ONA15 takeaways that local newsrooms will find helpful

By Nancy Yoshihara
10/5/2015 | 10:00 pm GMT

If you were unable to attend ONA15 in Los Angeles a week ago, you can catch the trends, highlights and...

A new digital planning tool turns 7,200 local websites into one marketplace

By Nancy Yoshihara
9/28/2015 | 10:00 pm GMT

LIONshare® is a free platform that makes fragmented local media easily identifiable and accessible to companies and retailers looking to...