+ All Categories
Home > Documents > Sentiment analysis

Sentiment analysis

Date post: 22-Feb-2016
Category:
Upload: elon
View: 88 times
Download: 0 times
Share this document with a friend
Description:
Sentiment analysis. Or, how to find happiness. Why do we want sentiment info?. Useful input for detection Brand sentiment Useful input for prediction Stock market, box office revenues, political outcomes Potentially for social uprisings, terrorist incidents. - PowerPoint PPT Presentation
Popular Tags:
24
Sentiment analysis Or, how to find happiness.
Transcript
Page 1: Sentiment analysis

Sentiment analysis

Or, how to find happiness.

Page 2: Sentiment analysis

Why do we want sentiment info?

• Useful input for detection– Brand sentiment

• Useful input for prediction– Stock market, box office revenues, political

outcomes– Potentially for social uprisings, terrorist incidents

Page 3: Sentiment analysis

What do you really want to know?

Page 4: Sentiment analysis

Brand satisfaction

Page 5: Sentiment analysis

Quality of life

Page 6: Sentiment analysis

Abstract predictor

Page 7: Sentiment analysis

Three considerations for a sentiment analysis system

• Data cleaning

• One piece of the puzzle

• Simple works best

Page 8: Sentiment analysis

Data cleaning (Because it’s a dirty world)

Page 9: Sentiment analysis

Data cleaning: on Twitter…

• Spam accounts

• Bots (Weather, sport, etc…)

Answer: a) http://trst.me/ (from infochimps)b) Make your own system

Page 10: Sentiment analysis

Data cleaning: from sentences to words

1. Tokenize the sentence(s) into words. (This may not be as easy as it seems).

2. Maybe do stopping/stemming, depending on application.

3. Pick a threshold of times we have to see a word in our training set, below which we ignore it.

4. Build a dictionary of words.

Answer: a) Twokenize.pyb) Write your own

Page 11: Sentiment analysis

One piece of the puzzle

Page 12: Sentiment analysis

Always make it part of a system

• When it’s wrong (and this is quite often) it will be very obviously wrong

• People don’t need to see this• This doesn’t actually detract from the utility of

the system

Page 13: Sentiment analysis

Success:

• Tracking political polls.• Predicting box office revenues.• Predicting the stock market.

Page 14: Sentiment analysis

Simple works best (for now)

Page 15: Sentiment analysis

The quick version

• Use supervised/semi-supervised learning method.

• For most cases I would recommend Naïve Bayes on the Bag of Words representation. Very simple to implement and near-best performance.

• If you don’t have any examples of happy/sad tweets (for your purpose), use known keywords, such as emoticons.

Page 16: Sentiment analysis

:)

Page 17: Sentiment analysis

^_^

Page 18: Sentiment analysis

:(

Page 19: Sentiment analysis

<3

Page 20: Sentiment analysis

:/

Page 21: Sentiment analysis

Things that don’t really help

• More advanced classifiers (eg SVMs)• Part of Speech tagging• Parse trees• Semi-supervised methods if you have very

large amounts of data

(Generally less than 2% improvement)

Page 22: Sentiment analysis

The formula for happiness

Page 23: Sentiment analysis

Basic positive/negative Twitter sentiment word list

• http://alexdavies.net/projects/twitter-sentiment-word-lists/

Page 24: Sentiment analysis

Thanks.


Recommended