From Wikipedia, the free encyclopedia
Jump to: navigation, search

MiTAP, or Mitre Text and Audio Processing, is a computer system that tries to automatically gather, translate, organize, and present information "for monitoring infectious disease outbreaks and other global events." [1] It is also used in the FBI Investigative Data Warehouse.


"Multiple information sources in multiple languages are automatically captured, filtered, translated, summarized, and categorized"[1]

It uses 'web sources, electronic mailing lists, newsgroups, news feeds, and audio-video data.'. The audio-video is automatically transcribed into text by the ViTAP system.[1]


In 2002 it was reported to have used CyberTrans, the Alembic natural language analyzer, WebSumm summarizer, Lucene indexing, NewsBlaster from Columbia, Brill tagging, SOAP, HTML, NNTP, Perl, Unix scripts, and other tools. Upgrades to various components are planned.[1]


It was created at the Mitre Corporation by Damianos and a team of other researchers, with public release in 2001.[1][2]


It is being used by the FBI as part of their Investigative Data Warehouse via DARPA's TIDES program.[3] According to 2004 FBI email, MiTAP was running at San Diego State University, collecting only English language website news. It mentioned a plan to have FBI run its own version of MiTAP.[4]

It has also been used by people in the White House, the Department of Homeland Security, the Pentagon,[1] the American Red Cross, the United Nations, and the European Disaster Center [5]


  1. ^ a b c d e f Damianos et al, AI Magazine, Vol 23, No 4 Cite error: Invalid <ref> tag; name "ReferenceA" defined multiple times with different content (see the help page).
  2. ^ Damianos et al, The MiTAP System..., 2004
  3. ^ FBI, IDW System Security Plan, 2003, and Security Concept of Operations IDW, 2004
  4. ^ EFF FOIA file, 2008 Apr 8, idw02. page 30 of linked pdf
  5. ^ Damianos et al. AI Magazine, Vol 23, No 4