What are they talking about?

Separating ideas from noise, on any subject, in any language.

How does it work? What's it for?

Check out these live examples of Sherlock at work

GOP Senators

Sherlock maintains and monitors a list of 50 Senators.

Democrat Senators

Currently 49 on a list we curate

Brexit Poll example

Sherlock can exploit a geographical filter which returns Tweets sent from within a user defined circle anywhere on the planet. We tried an open-ended poll across each constituency on mainland Britain. Here's an interactive map with the results.

The European Union & AI

Sherlock's designer, Chris Painter, is a proud member of the European Union Artificial Intelligence Alliance, and fully supports the EU drive towards explainable artificial intelligence.

In January 2019 an EU AI initiative, eu4ai, launched in Barcelona an information campaign aimed at raising commercial awareness of AI, particularly among smaller companies

Click here for Sherlock's take on the tweets of eu4ai, and AI News in English, from actuia.com in France

GOP Representatives

223 Representatives also monitored 24/7

Democrat Representatives

211 on a list we curate

 #UK Conservatives

List by Tweetminster

 #UK Labour

List by Tweetmister

Text mining for ideas

It may sound odd to think of an idea as something that can be found in text, but that is how we store and transfer group ideas, packaged in sequential nested chunks that make them easier to digest. Once the packaging is removed the patterns emerge, as words that are frequently seen together to denote the underlying idea.

The word "idea" is derived from old Greek that means "to have seen". If you want to hear how noticing coincidences formed the original notion of 'idea', and how it remains central to Cognitive Science, check out this podcast from Oxford's Bettany Hughes

Ethical by design

Sherlock finds the common ideas that bind groups together, and needs no further information than the words written. 

The process is easily explained, and fully traceable, because the answers are in the sources, verbatim.

It doesn't need, use,  or store private data. Privacy is baked into the design.

Always up to date

If an earthquake occurs, or a new political sensation invades the press, new names will baffle supervised text-mining techniques. Sherlock works from a list of what to ignore, so new stuff gets handled automatically, just so long as it is frequent.

Multilingual

Sherlock has been tried on more than thirty languages, including Arabic and Russian. It is completely grammar agnostic, and will work on any language, human or computer, for which a stop word list can be provided.

Balanced

Sherlock tries to be as autonomous as possible, requiring just two parameters, how robust the patterns need to be. and how many words will be enough.  For example, the survey takes 75% pattern confidence, and 20 words

© Copyright 2014-2019 meme-machines.com - All rights reserved.