«
»

Sentiment analysis of Tyre competitors from Twitter and R

Below a simple example of sentiment analyis of tweets about tyre competitors. Notes:

  • x-axes=positive tweets
  • y-axes=negative tweets
  • positive and negative words: Hu and Liu’s “opinion lexicon” categorizes nearly 6,800 words as positive or negative and were downloaded from Bing Liu’s web site: http://www.cs.uic.edu/~liub/FBS/opinion-lexicon-English.rar
  • only more positive and worst negative tweets are collected

The code can be found here.

 

This entry was posted on Sunday, February 12th, 2012 at 18:00 and is filed under Me. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.

2 Responses to “Sentiment analysis of Tyre competitors from Twitter and R”

  1. Gabriele Martinelli says:
    16/02/2012 at 11:09

    ciao, non e’ che per caso sai se esiste una lista simile di parole positive/negative anche in italiano? grazie!

  2. tm says:
    17/02/2012 at 21:34

    Interesting use… This exact twitteR package and the Hu/Liu corpus were the inspiration for a Twitter sentiment analysis Android app we wrote called TxtMiner, http://bit.ly/Axxoju

Leave a Reply