2
1

I use both rattle and rapidminer I would like to know some startup steps to hack existing code and bit of tutorial on sentiment analysis for twitter data.

Thank you

asked 08 Feb '11, 23:37

vasundhar's gravatar image

vasundhar
46127
accept rate: 0%


While I wouldn't say it's the best resource, a lot of people like my posts on using text classification for sentiment analysis:

  1. Using a Naive Bayes Classifier
  2. Precision and Recall
  3. Bigrams and Collocations
  4. Eliminate Low Information Features

I also have a demo and an API where this has been put into practice.

link

answered 14 Feb '11, 04:46

japerk's gravatar image

japerk
51229
accept rate: 0%

edited 21 Feb '11, 20:16

Hi Japerk, Thank you for the inputs, Your 4th link seems broken.

(21 Feb '11, 20:04) vasundhar

fixed the 4th link

(21 Feb '11, 20:17) japerk

For projects where all that's needed is some indication of Sentiment from Twitter I've used TwitterSentiment's API at http://twittersentiment.appspot.com/

See 'about' for details of the API and background information on the theory and approaches taken.

link

answered 14 Feb '11, 19:31

Tim%20Davies's gravatar image

Tim Davies
145117
accept rate: 10%

Thanks Tim, Appreciate it.

(21 Feb '11, 20:04) vasundhar

I Found good twitter Sentiment Analysis done on Airlines Here It is based on R very good starter tutorial

link

answered 29 Jul '11, 09:02

vasundhar's gravatar image

vasundhar
46127
accept rate: 0%

Your answer
toggle preview

Follow this question

By Email:

Once you sign in you will be able to subscribe for any updates here

By RSS:

Answers

Answers and Comments

Markdown Basics

  • *italic* or _italic_
  • **bold** or __bold__
  • link:[text](http://url.com/ "title")
  • image?![alt text](/path/img.jpg "title")
  • numbered list: 1. Foo 2. Bar
  • to add a line break simply add two spaces to where you would like the new line to be.
  • basic HTML tags are also supported

Tags:

×5
×3
×2
×1

Asked: 08 Feb '11, 23:37

Seen: 2,888 times

Last updated: 31 Jan, 07:34

powered by OSQA