sentimentr icon indicating copy to clipboard operation
sentimentr copied to clipboard

Published 20 hours ago • verified publisher icon trinker

Include sarcasm in the algorithm

Open trinker opened this issue 8 years ago • 4 comments

  • http://www.cs.utah.edu/~huangrh/official-sarcasm-cameraReady-v2.pdf
  • http://stackoverflow.com/questions/14097388/can-an-algorithm-detect-sarcasm

Difficult task for 100% accuracy but there may be key features that are highly correlated with a sarcastic comment that would improve sentiment detection. The idea isn't super accuracy of sarcasm detection...just adding accuracy to the sentiment detection by identifying very likely sarcastic phrases.

Possible leading ngrams to consider:

  1. I (love|like) how (negative situation)
  2. As if (pronoun/proper noun)
  3. It's (really|so)* (awesome|great) how (negative context)

trinker avatar Jan 03 '16 15:01 trinker

Thinking to not include in algorithm but as a separate detector.

trinker avatar Feb 11 '17 22:02 trinker

Thinking to not include in algorithm but as a separate detector.

when this functionality is planned to be released, at least for beta testing?

bazarnov avatar Mar 18 '19 16:03 bazarnov

@bazarnov This is a difficult problem. There are no current plans to release this feature.

trinker avatar Mar 18 '19 17:03 trinker 

	Could you please advice are there any available solutions among any available R packages for this kind of task?

On Mon, Mar 18, 2019 at 7:07 PM +0200, "Tyler Rinker" [email protected] wrote:

@bazarnov This is a difficult problem. There are no current plans to release this feature.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.

bazarnov avatar Mar 18 '19 19:03 bazarnov