News
Category: Research technologies
-
New research paper from Security Force Monitor: using Natural Language Processing to extract knowledge graphs about police and army units and their commanders
Security Force Monitor has published a technical working paper on Natural Language Processing (NLP) and our research into abuses by police and armies. It shows how a NLP system can be deployed to extract information from sources on security force units and their related personnel. This is a practical contribution into the ongoing conversation about the tactical use of AI in human rights work.
-
A French translation of WhoWasInCommand, an overhauled Research Handbook, and other updates
WhoWasInCommand can now be used in French. We've also updated our Research Handbook. Read on...
-
Unlocking the Department of State’s foreign military training data for good this time
Security Force Monitor has crunched 5,600 pages of State Department PDFs to create new version of the U.S. foreign military training data. Today we release a tool to explore these 200,000 rows of data.
-
WhoWasInCommand shows you all the sources that evidence every piece of data – but you probably missed the way it does this
Here's how to see all the sources our researchers used to evidence every single piece of data on WhoWasInCommand.
-
OpenStreetMap is (sometimes) a handy database of military and police locations – here’s how to see them
OpenStreetMap is a useful tool for getting an impression of a security force's bases and physical infrastructure. How do we do this?
-
Not all snapshots are created equal – a time-saving Wayback Machine technique
Image: Clipping from 8 February 2004 Wayback Machine snapshot of SEDENA army commanders page. How do we get all the data out of that and 50 other captures of the same page? We’re going to write about our...
-
Analysis of sources for data on security forces: can computers help us out?
Can computers help Security Force Monitor’s researchers increase the speed and accuracy of extracting relevant data about security forces from the text of news articles and reports?