SENTIMENT ANALYSER
Presented By:
Akash Prajapati
1309113008
Ankit Raj
1309113012
Objective
 The project mainly deals analysis of product reviews from various
ecommerce websites.
 Our Main objective is to get the overall polarity of reviews for a
particular product.
Sentiment Analysis
 Identify the orientation of opinion in a piece of text
 Can be generalized to a wider set of emotions
The movie
was fabulous!
The movie
stars Mr. X
The movie
was horrible!
[ Factual ][ Sentimental ] [ Sentimental ]
References: google images
Sentiment Analysis
 Movie: is this review positive or negative?
 Products: what do people think about the new iPhone?
 Public sentiment: how is consumer confidence?
Is despair increasing?
 Politics: what do people think about this candidate or issue?
 Prediction: predict election outcomes or market trends
from sentiment
4
Sentiment analysis has many
other names
Opinion extraction
Opinion mining
Sentiment mining
Subjectivity analysis
5
Google Product Search
Reference: google Images
Use Case Diagram
Texts
Sentences
Noun
Adjective
Positive Neutral Negative Polarity
Screen Shots
Result
Software Specification
 FRONT END : HTML,CSS,JavaScript
 BACK END : Python , Django
 PLATFORM : Windows,Ubuntu
Code Description:
 processReview function:
 Input::
 Output::
.
 getFeatureVector function
.
 featureList(removes repetition)
 Input::
 Output::
.
 Training set::
.
 NBClassifier: It is a pointer to the
nltk.NaiveBayesClassifier.train(training_set) object::
.
.
Main Code
.
 .
.
.
.
.
CONCLUSION AND FUTURE WORKS
 Sentiment analysis or opinion mining is a field of study that
analyzes people’s sentiments, attitudes, or emotions towards
certain entities. This project deal with a fundamental problem of
sentiment analysis, sentiment polarity categorization. Online
product reviews from Amazon.com are selected as data used for
this project.
 We plan to use more exhaustive techniques in future to build a
full-fledged model that is able to analyse a large set of data in a
little time and with good accuracy.
References
 https://www.djangoproject.com/
 https://www.python.org/
 https://plot.ly
 https://docs.python.org/3/tutorial/
 https://www.nltk.org/
Thank You

Sentiment Analyzer