NewsEngin Inc.

Smart tools for news people

CatScan is a high-speed categorization and scanning engine that can peer inside and characterize every document that flows through a newsroom.

CatScanCatScan tells you what every staff-produced story or other document is about, based on the news-industry standard IPTC NewsCodes, a thoughtfully designed hierarchy of about 1,400 subject classifications. This set of categories is fully customizable. In addition, the software scans every document to identify organizations, places and people that matter to you. The list of entities for which you’re scanning can update automatically from external sources.

CatScan features an elegant, informative front-end that makes it easy for a user to tell CatScan why one story belongs in a particular category and why another one doesn't. People tell CatScan what phrases to look for and how much they matter, and from that point on the software nails the categories with remarkable accuracy. No arcane algorithms, no fuzzy logic. Just common sense. CatScan is unlike other categorization engines that might be able to analyze one or two documents per second. CatScan can categorize and scan 20 typical news stories or press releases per second while running on modest, affordable hardware. That’s more than 1 million documents per day.