Thursday, October 28, 2010

Twitter and Universal Human Study


The mood on Twitter predicts what's going to happen in the stock market with 87 percent accuracy.
Researchers from Indiana University analyzed the tweets of 2.7 million Twitter users in 2008, dividing them into six categories of emotions. They were surprised to find that the higher percentage of "calm" tweets on a given day, the higher the Dow Jones Industrial Average was in the following two to six days. In fact, this method yielded a 87.6 percent rate of accuracy.
It was one of those "Eureka" moments Bollen probably should have kept to himself. (And then profited from.)



More than 70 percent of tweets get no reaction from one's followers.

Sysomos, a market research company that specializes in social media, examined 1.2 billion tweets posted over a two-month period. It found that only 6 percent of tweets get retweeted, and only 23 percent garner replies.
We are a bit surprised that even that many tweets get attention. We figured the percentage would be lower. Still, the number of more-or-less ignored words that have been published by the Internet generation is staggering.




  • Earlier studies had found that blogs can be used to gauge public mood, and that tweets about movies can predict box office sales
  • Some reluctant to believe that the moods captured on Twitter can cause the stock market to change. Not everyone on Twitter plays the stock market.
  • Behavioral economics tells us that emotions can profoundly affect individual behavior and decision-making. Does this also apply to societies at large, can societies experience mood states that affect their collective decision making?
  • There have been many other social phenomenon that researchers have claimed could predict the stock market. Sports events like the Super Bowl, the NY Mets winning the playoffs.
  • The overlap for ‘Calm’ and Dow isn’t perfect, but it doesn’t have to be. Rather than try and create a program that simply uses tweet analysis to predict stocks, the research team was interested in augmenting other prediction algorithms. 
  • Aku rasa Twitter ni lebih kurang sama dengan Facebook. Facebook ada smiley. Try pilih satu hari, contoh Isnin awal bulan, buat post-post gersang, contoh 'aku perlukanmu', 'I'm lonely', 'where are you', mesti penganalisis ingat tu musim mengawan rakyat Malaysia.

`It's Like the Matrix:' Twitter May Help Read Investors' Minds









Labels: ,

2 Comments:

Blogger Syed Ahmad Fathi said...

Hidup twitter!

October 30, 2010 at 1:31 PM  
Anonymous akmal said...

haha..ko x abis2 post kat twitter

October 31, 2010 at 5:17 AM  

Post a Comment

Subscribe to Post Comments [Atom]

Links to this post:

Create a Link

<< Home