[Air-L] analytical tools for emojis, textual expressions of emotions?

[Charles M. Ess]

Dear AoIRists,

one of our MA students is exploring the role of diverse emotions - first 
of all, anger - in responses to news stories on three major Norwegian 
news sites.  The broad hypothesis is that anger will be most prevalent 
and effective in catalyzing further response (including sharing, likes, 
etc.) - but four emotions total are taken on board: sadness, anger, 
surprise, and happiness.

1) There is an online tool available for analyzing the emotive content 
of texts - "The SATI API enables to perform Sentiment Analysis from 
Textual Information", etc.  Comments and observations on its utility, 
validity?

2) Recommendations, please, for either useful examples of similar 
research, especially with a view towards methods of accumulating and 
then analyzing emoticons, and/or other suggestions regarding possible tools?

Many thanks in advance,
- charles ess
-- 
Professor in Media Studies
Department of Media and Communication
University of Oslo
<http://www.hf.uio.no/imk/english/people/aca/charlees/index.html>

Postboks 1093
Blindern 0317
Oslo, Norway
c.m.ess at media.uio.no