Comments on: Sentiment analysis in text

By: CJ

CJ — Mon, 27 Jul 2009 05:09:47 +0000

Thank you Dana for the kind words and for the fabulous input

By: Dana Lookadoo

Dana Lookadoo — Sun, 26 Jul 2009 05:50:43 +0000

CJ,

I so enjoyed this post and your sharing it on my blog. I especially liked your thought, “how do you pick out affective or emotive words as opposed to generic ones?” Such has been the challenge for Social Media Monitoring tools. I wanted to share that Sentiment Metrics, http://www.sentimentmetrics.com/, recently launched as one tool that attempts to monitor sentiment, primarily for reputation management. Other tools are trying, and I use Raven Tools for social monitoring, yet one must subjectively apply a sentiment measurement to each social mention.

Now, your point about the clustering possibilities for search engines is an eye-opener! I’m shaking my head in agreement and sending a high five for your great insight!

By: CJ

CJ — Sat, 24 Jan 2009 05:22:00 +0000

Hey Bob,

thanks for adding that. I also agree with you.

cj

By: Bob Carpenter

Bob Carpenter — Fri, 23 Jan 2009 20:56:00 +0000

Our natural language processing API, LingPipe, has a tutorial on sentiment analysis including source code that recreates the Pang and Lee experiments.

My favorite papers on sentiment lately have been Ryan McDonald's. The Blitzer et al. paper is nice for the examples, but I don't think it's worth doing adaptation when training data's so cheap.

By: CJ

CJ — Thu, 22 Jan 2009 16:45:00 +0000

I’m glad you found it useful! I’d be interested in what you conjure up if you feel like sharing

By: Arturo Servin

Arturo Servin — Thu, 22 Jan 2009 14:26:00 +0000

What a coincidence. Today in the morning I was thinking about how to do something like this with twitter. It was just a thought but I am glad that you posted some references to start digging.

Regards,
-as