Comments on: Using Twitter to predict stock moves http://blogs.reuters.com/felix-salmon/2010/12/23/using-twitter-to-predict-stock-moves/ A slice of lime in the soda Sun, 26 Oct 2014 19:05:02 +0000 hourly 1 http://wordpress.org/?v=4.2.5 By: jmedia http://blogs.reuters.com/felix-salmon/2010/12/23/using-twitter-to-predict-stock-moves/comment-page-1/#comment-22231 Fri, 24 Dec 2010 00:59:03 +0000 http://blogs.reuters.com/felix-salmon/?p=6700#comment-22231 We are seeing much more mood reactions to stock, usually driven by media stories. Twitter seems to be the second wave of mood and investment reaction. If you analyze company-specific information, news articles and return the “media mood” you get a much clearer picture.

FlameIndex.com is a source that seems to be getting much closer to predicting what is about to happen on Twitter. It analyzes 10 K media sources per day and ranks companies based on how “on fire” they are in the media. It filters up the news articles as well. Now all they need is a stock overlay and we’ll be able to see the correlation instead of doing the calculations by hand.

]]>
By: mktsentiment http://blogs.reuters.com/felix-salmon/2010/12/23/using-twitter-to-predict-stock-moves/comment-page-1/#comment-22230 Fri, 24 Dec 2010 00:11:55 +0000 http://blogs.reuters.com/felix-salmon/?p=6700#comment-22230 Doing this with non-stock market specific tweets is meaningless. People may be “not calm” or calm for many reasons, especially teens and colleges kids with BF and GF, drugs and other growing issues, and most don’t even buy stock.

On the other hand, if you analyze stock-specific sentiment using natural language understanding and domain-specific knowledge, such as knowing the meaning of buying a call, selling a put, issuing dividends, targets and expectations, etc., the analysis and correlation will be more meaningful. That’s what mktsentiment.com does. We have found filtering rules that have proven to be very effective and can be a useful supplement to other technical indicators.

Spams are not a problem because each source is weighted by a vector and the spams are weighed zero or close to zero. Echoes are detected and treated differently too.

]]>
By: LaurenDill http://blogs.reuters.com/felix-salmon/2010/12/23/using-twitter-to-predict-stock-moves/comment-page-1/#comment-22216 Thu, 23 Dec 2010 15:25:41 +0000 http://blogs.reuters.com/felix-salmon/?p=6700#comment-22216 This is a really interesting concept. I know Twitter ‘blew up’ this year, but I had no idea you could apply concepts from it to other parts of business. I’m putting my money on Google to rule the universe.

]]>