1. Sentiment Analysis Positive: love, best, cool, great, good, amazing
Negative: hate, worst, terrible, awful, nightmare

2. Software Online Twitter Sentiment Accessing Sentiment140 with an API
R Example: Airlines
Reference: Vendors
Text-Specific
Sematria  Excel
SmartLogic
Provalis
Lexalytics
Statistical Software
SAS
IBM
Angoss

3. Online Sentiment Analysis
2015
2016

4. Online Sentiment Analysis

5. Sentiment140 API

6. R: Sentiment140 it uses free sentiment140 service
they do vocaburay training, syntax of hash, http link etc.
require(devtools) install_github("sentiment140", "okugami79") # sentiment analysis library(sentiment) sentiments <- sentiment(cold_weather_df$Tweets) table(sentiments$polarity)

7. 169,104
Views

10. Game Plan Search Twitter for airline mentions & collect tweet text
Score sentiment for each tweet
Summarize for each airline
Compare Twitter Sentiment with ACSI Satisfaction Score
Load sentiment word lists
Scrape ACSI web site for airline customer satisfaction scores

11. Airlines top customer satisfaction... alphabetically3

12. which gives us plenty to listen to
Completely unimpressed Poor communication, goofy reservations systems and all to turn my trip into a mess.
Publicly pledging to never again. The worst airline ever. U have lost my patronage forever due to ur incompetence
@united #fail on wifi in red carpet clubs (too slow), delayed flight, customer service in red carpet club (too slow), hmmm do u see a trend?
@United Weather delays may not be your fault, but you are in the customer service business. It's atrocious how people are getting treated!
We were just told we are delayed 1.5 hrs & next announcement - “We're selling headsets.” Way to capitalize on our misfortune.
@SouthwestAir I know you don't make the weather. But at least pretend I am not a bother when I ask if the delay will make miss my connection
@SouthwestAir
I hate you with every single bone in my body for delaying my flight by 3 hours, 30mins before I was supposed to board. #hate
- you suck! Your prices are over the moon & to move a flight a cpl of days is $ Insane. I hate you! U ruined my vacation!

13. twitteR
twitteR

14. Sentiment List
This list was compiled over many years starting from our first paper (Hu and Liu, KDD-2004).
Around 6800 words
# add a few twitter and industry favorites
pos.words = c(hu.liu.pos, 'upgrade')
neg.words = c(hu.liu.neg, 'wtf', 'wait', 'waiting', 'epicfail', 'mechanical')
Paper:

15. Sentiment Score Compare Tweets to Sentiment List
american.scores = score.sentiment(american.text, pos.words, neg.words, .progress='text')
score.sentiment = function(sentences, pos.words, neg.words, .progress='none') { .
pos.matches = match(words, pos.words)
neg.matches = match(words, neg.words)
score = sum(pos.matches) - sum(neg.matches)
return(score) }
Compare Tweets to Sentiment List
Sum up the Number of Matches: Subtract Positive - Negative
Example

16. Histogram of Sentiment Score

17. Comparison of Twitter to Survey

18. Appendix: Vendors

19. Online Sentiment Analysis
Jul 15, 2014

20. Sentiment Analysis

22. Text Analytics for Excel