From 77e0614b2de12717c677b47ef5f3fcd6f8a2a880 Mon Sep 17 00:00:00 2001 From: Mengxuan Xia Date: Thu, 6 Apr 2017 21:14:11 -0400 Subject: [PATCH] added caveat regarding off-the-shelf solution --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index cee0179..41bdac4 100644 --- a/README.md +++ b/README.md @@ -72,6 +72,8 @@ Stanford Sentiment Treebank: Sentiment dataset with fine-grained sentiment annot The characteristics of each implementation are described. +_**Caveats**: A key problem in sentiment analysis is its sensitivity to the domain from which either training data is sourced, or on which a sentiment lexicon is built. [[♠]](http://www.springer.com/gp/book/9783319389707) Be careful assuming off-the-shelf implementations will work for your problem, make sure to look at the model assumptions and validate whether they’re accurate on your own domain [[♦]](https://lobste.rs/s/zsfqyk/curated_list_sentiment_analysis_methods/comments/ge671n#c_ge671n)._ + ### NodeJS [thisandagain/sentiment]( https://github.com/thisandagain/sentiment): Lexical, Dictionary-based, AFINN-based.