For 140 characters, Twitter can tell us a lot about ourselves.

By looking at masses of tweets, word-crunching software can tell when we’re feeling up or down, help us decide what stocks to buy or sell, and track the spread of illness through a population.

Linguist Daniel Midgley puts it all together on this week’s Talk the Talk.


Listen to this episode

42: Learning from Twitter

Download this episode

You can listen to all the episodes of Talk the Talk by pasting this URL into your podlistener.

http://danielmidgley.com/talkthetalk/talk_classic.xml

Show notes

PC World article:
http://www.pcworld.com/article/240831/twitter_analysis_reveals_global_human_moodiness.html

This New York article has some stats about tweet numbers:
http://nymag.com/news/media/twitter-2011-10/

But why not check them out yourself?
http://hide.dnsalias.net/tweetcounter/index-en.cgi

Twitter and trading
http://www.cnbc.com/id/41948275/How_Twitter_Is_Transforming_Trading_in_Commodities

Twitter and health
http://scopeblog.stanford.edu/2011/07/mining-twitter-for-public-health-information/

One NLP project about using Twitter to recognise named entities to help during emergencies (PDF)
http://aclweb.org/anthology/W/W10/W10-0512.pdf