News, social media posts, invoices, technical and company reports, catalogues, press releases, PDFs of every shape and size… we’re all surrounded by documents and text full of valuable content which can’t be used for systematic data analysis because it’s in the wrong structure.

With Hivemind CORE, you can transform the relevant parts of the text, tables, charts and infographics in documents like these into a structure designed specifically for your project.

Use cases

From PDFs

From PDFs

Extract useful, structured data from the mix of text, images, tables and infographics found in both native and scanned PDFs. Hivemind's CEO, Dan Mitchell, discusses how CORE can help you do this in his blog 'The key to unlocking your PDFs'.

From news

Extract relevant structured data from huge volumes of information by filtering articles for relevance and then extracting data or assessing sentiment in a highly configurable manner. This demo video explains how to set up a news collection task, using CORE.

From websites

Harvest and structure information from around the web: collect documents from a variety of sites, gather information from social media posts, or create a web-monitoring or scraping process impervious to a site’s structural changes. This demo video explains how to set up a task to collect information from company websites, using CORE.
talk to the hivemind team

From filings

Cross-check numerical data in your regular data feed, create structure around the information provided in footnotes or other text, or create sophisticated event-based datasets based on regulatory announcements. This demo video explains how to set up a task to extract share information from filings, using CORE.
talk to the Hivemind team


Request a demo