Sentiment Service for Social Media Data
Description:
Social Media Data like Facebook, Twitter, blogs, etc. is currently growing in an exploding speed. Understanding their sentiments could help us mine knowledge and capture their ideas without necessarily going through all data, which will save us a huge amount of time. Understanding their sentiments could help us mine knowledge and capture their ideas without necessarily going through all data, which will save us a huge amount of time. This web tool is developed for: [1 identifying language for input sentence:, 2: identifying sentiment input sentence.]. The experiment results on primary social media data like Facebook comments and twitter tweets show that we get highly accurate sentiment identification.
Publications:
These data sets were introduced in the following papers:- Kunpeng Zhang, Yu Cheng, Yusheng Xie, Ankit Agrawal, Diana Palsetia, Kathy Lee, and Alok Choudhary, SES: Sentiment Elicitation System for Social Media Data, ICDM-SENTIRE 2011. pdf
- Kunpeng Zhang, Yu Cheng, Wei-keng Liao, Alok Choudhary, Mining Millions of Reviews: A Technique to Rank Products Based on Importance of Reviews, ICEC 2011. pdf
Data Download:
- The data used in our experiments is available here
- Usage:
- Sentence batch example: [{"id": 234383684260741121,"text": "@b3LIEv3r It's pretty spartan these days: Distressor, c-800 mic, a couple guitars, a drum kit, a piano, my laptop, and an m-audio keyboard."}]
- Rate Limiting: (1)per user: each user can send 1000 sentences; (2)perl requests: in each request, the maximum sent sentences is 100; (3)rate: you can not send more than 100 requests per minute
