Sentiment tool Project presentaion

SENTIMENTAL ANALYSIS TOOL

BY:-RAVINDRA CHAUDHARY

SACHIN SINGH

UNDER THE GUIDENCE OFMRS. SMITA TIWARI

CONTENT• Introduction•Problem Statement•Objective• Tools/Techniques•Methodology• Implementation•Results & Discussion•Conclusion• Future Scope of the project

INTRODUCTIONWhat is Sentiment Analysis…??

It is the classification of the polarity of given text in the document.The goal is to determine whether the expressed opinion in the text is

Positive , Negative or Neutral.

For Example:- Positive :- sarvjeet is good guy…negative :- jasleen is misusing the law..Neutral :- waiting for court decision..

Why using twitter for sentiment analysis:-

• Social networking and microblogging website.• Short text messages 140 Character.• 316+ million active users and 500 million tweets per day generated • People share their thoughts using twitter it may be any social

issue ,movie ,politics , news and so on.• Also share current affairs and personal view on different topics..• The challenge is to gather all such relevant data , detect and

summarize the overall sentiment on a topic.

Problem Statement

• The problem in the sentiment analysis is classifying the polarity of given text in a document in a sentence

• Whether the expressed opinion in the document or in a sentence is positive ,negative or neutral.

Objective

• To implement an Algorithm(Naïve Bayes algorithm) for classification to text into Positive , Negative ,or Neutral.• Making more data set for more accurate results.

Naïve Bayes Classifiers

• In machine learning, naive Bayes classifiers are a family of simple probabilistic classifiers based on applying Bayes' theorem with strong (naive) independence assumptions between the features• Naive Bayes has been studied extensively since the 1950s. It was

introduced under a different name into the text retrieval• community in the early 1960s, and remains a popular (baseline)

method for text categorization,

• the problem of judging documents as belonging to one category or the other (such as spam or legitimate, sports or politics, etc.) with word frequencies as the features• Naive Bayes classifiers are highly scalable, requiring a number of

parameters linear in the number of variables

NAÏVE BAYES EXAMPLE:-

Tools/Techniques

• NET BEANS IDE 8.0• WAMP SERVER • MY SQL• HTML5• CSS• JAVA

Methodology

Methodology

1. DATA COLLECTION• download the tweets using Twitter 4J API.

2. TOKENSIER• Twitter using POS(part of speech) tagger..

3. PRE-PROCESSING• Remove slag words.• Remove URL and HASTAG(#),numbers.• Replace sequence of repeated character coooooool by cool.• Remove noun and prepositions

FEATURE EXTRACTION• Percentage of capitalized word• No of –ve /+ve capitalized word• No of +ve /-ve hashtag• No of +ve /-ve emoticons• No. of negations• No. of special characters ex..@#%^*

CLASSIFICATION AND PREDECTIONS

• The model is built to predict the sentiment of new tweets…• Feature extracted are next focused to classifier

HOME page

Types of Classification

1. Binary classification:- only Positive , Negative .

2. 3 Teir:- Positive , Negative and Neutral .

3. 5 Teir :- :- Extremely Positive , Extremely Negative , Positive , Negative

and Neutral

Future scope

• Web application can be converted to mobile applications• Sentiment analysis may be implemented in future for accuracy

purposes• Updating dictionary for new synonyms and antonyms

Conclusion

By improving the data sets we get more accurate results (sentiments).

THANKYOU EVERYONE