The document outlines a presentation on sentiment analysis of tweets using Python and NLTK, focusing on classifying tweets as positive or negative. It discusses the necessity of training a classifier with manually classified tweets, the extraction of features from the tweets, and utilizes a Naive Bayes classifier to determine the sentiment based on the frequency of words. An example is provided to demonstrate how the classifier identifies the sentiment of a tweet by analyzing the presence of certain words.

1. Twitter Sentiment Analysis using
Python and NLTK
Presentation by:
ASHWIN PERTI,
Department of IT

2. Sentiment Analysis using PYTHON
The purpose of this Sentiment Analysis is:
● Able to automatically classify a tweet as a
positive
OR
● Negative tweet Sentiment wise

3. Sentiment Analysis using PYTHON
● The classifier needs to be trained:
● We need a list of manually classified tweets.

4. Positive Tweets
● I love this car
● This view is amazing
● I feel great this morning
● I am so excited about the concert
● He is my best friend

5. Negative Tweets
● I do not like this car
● This view is horrible
● I feel tired this morning
● I am not looking forward to the concert
● He is my enemy

6. Test Tweets
● TEST SET – to assess the exactitude of the
trained classifier
● I feel happy this morning. positive
● Larry is my friend. positive
● I do not like that man. negative
● My house not great. negative
● Your song annoying. negative

7. CLASSIFIER
● The list of word features need to be extracted
from the tweets.
● It is a list with every distinct words ordered by
frequency of appearance.

8. CLASSIFIER – Feature Extractor
● To decide which features are more relevant.
● The one we are going to use returns a
dictionary indicating that words are contained
in the input passed.
● INPUT - tweet

9. classifier=nltk.NaiveBayesClassifier.
train(training_set)

10. Naive Bayes Classifier
● It uses the prior probability of each label – which is
the frequency of each label in the training set and the
contribution from each feature.
● In our case, the frequency of each label is the same
for 'positive' and 'negative'.
● Word 'amazing' appears in 1 of 5 of the positive
tweets and none of the negative tweets.
● This means that the likelihood of the 'positive' label
will be multiplied by 0.2 when this word is seen as
part of the input.

11. CLASSIFY
● Now that we have our classifier initialized,
● Classify a tweet and
● See what the sentiment type output is:
● Our classifier is able to detect that this tweet
has a positive sentiment because
● Of the word 'friend'
● Which is associated to the positive tweet:
● 'He is my best friend'

12. print extract_features(tweet2.split())
● 'contains(looking)': False,
'contains(feel)': False,
● 'contains(the)': False,
● 'contains(excited)': False,
● 'contains(about)': False,
● 'contains(great)': False,
● 'contains(horrible)': False,
● 'contains(car)': False,
● 'contains(this)': False,
● 'contains(best)': False,
● 'contains(friend)': True,
● 'contains(concert)': False,
● 'contains(forward)': False,
● 'contains(view)': False,
● 'contains(tired)': False,
● 'contains(like)': False,
● 'contains(love)': False,
● 'contains(amazing)': False,
● 'contains(enemy)': False,
● 'contains(not)': True,
● 'contains(morning)': False}