[ambiate]

I just listened to a lecture on this at BU. Emerging Internet Technologies at IBM or something of that nature. He was basically trying to sell us his product that crawled the internet (mainly a firehose at Twitter) and gathered statistics for advertisers and presented it in pretty graphics.

The main issue they had was developing language recognition. Deciding if a user 'liked', 'loved', 'hated' or was 'neutral' about a product. Another issue that stood out to me had to do with their reliance on the internet. Just because 200 users tweeted that 'this movie is going to suck' does not really represent the overall opinion.

To reiterate, the whole buzz of the lecture was the biggest turn off. He wasn't explaining about how to expand on his product or where to go from here. Just that they had developed a product and we could use it instead of attempting to develop one ourselves.

[ohashi]

Maybe 200 is too small a sample size, but you can glean and predict stuff with that sort of data. My master's thesis was about predicting box office sales based off twitter data. (coincidentally these guys published a couple months before me: http://www.fastcompany.com/1604125/twitter-predicts-box-offi...) but we had incredibly similar results. It is pretty interesting to see what you can do with that data.

If it makes you feel any better, you can build it yourself, I certainly did. I didn't even use any libraries like NLTK to build my sentiment analysis. Read some research papers and built it from scratch (code wise at least, the ideas used were fairly common). It's a fun challenge. I still work with that code every day and use it in my startup now :)