Scribd
Upload
62 views8 pages

Synopsis

This project aims to perform sentiment analysis on movie reviews from IMDb to classify reviews as positive or negative. The methodology will use machine learning classifiers like Naive Bayes, logistic regression, and support vector machines trained on review data. The objectives are to analyze features that affect movie scores and determine the best performing classifier based on accuracy. The document outlines the introduction, literature review, objectives, methodology, and references for the project on automated sentiment analysis of IMDb movie reviews.

Uploaded by

Shivam Singh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
62 views8 pages

Synopsis

This project aims to perform sentiment analysis on movie reviews from IMDb to classify reviews as positive or negative. The methodology will use machine learning classifiers like Naive Bayes, logistic regression, and support vector machines trained on review data. The objectives are to analyze features that affect movie scores and determine the best performing classifier based on accuracy. The document outlines the introduction, literature review, objectives, methodology, and references for the project on automated sentiment analysis of IMDb movie reviews.

Uploaded by

Shivam Singh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 8

SENTIMENT ANALYSIS OF

IMDb REVIEW

PROJECT SYNOPSIS

OF MAJOR PROJECT

BACHELOR OF TECHNOLOGY

IN

COMPUTER SCIENCE AND ENGINEERING

SUBMITTED BY

YASH DIXIT SHIVAM SINGH VASUPANDEY

SAKSHI CHAUHAN SURAJ KR. SHARMA

Greater Noida Institute of Technology, Greater


Noida Dr. A.P.J. Abdul Kalam Technical
University, Lucknow
TABLE OF CONTENTS

Content Page No.


Introduction to the project

Literature Review

Objectives

Methodology

References
Introduction to the project

IMDb is an entertainment review website where people leave their


opinions on different movies and shows. You can perform sentiment
analysis on the reviews present there as well.
Reviews of shows and movies help production companies in
understanding why their title failed (or succeeded). 
Sentiment analysis, also known as opinion mining, is a natural
language processing (NLP) technique used to determine the sentiment
expressed in textual data. It involves classifying text into categories
such as positive, negative, or neutral, to understand the overall
sentiment of a particular piece of text.
In this project we will be using jupyter notebook as the IDE and
python libraries such as pandas , matplot.lib , numpy etc . Data set is
taken from kaggle which is authentic. Machine learning (ML)
algorithms can be employed to automate this process and provide
accurate sentiment analysis results. This synopsis presents a project on
sentiment analysis using ML techniques.
Literature Review

(write something 1 page about article,ppr,method,etc)


OBJECTIVE

Movies are the most convenient ways to the people for entertainment.
But only a few movies are successful and are rated high. There are
many ratings websites that will help the movie fanatics to decide
which movie they should watch and which they should not. Websites
like IMDB, Rotten tomatoes, etc. are the leading ones amongst those.
The rating on these websites determine the success of the movie by
giving it a score out of 10 based on the stars given by the viewers. But,
there isn’t any method that can provide the prediction based on movie
reviews. So, to determine the success of the movie based on reviews,
sentiment analysis comes into picture. Sentiment analysis is the
interpretation and classification of emotions within text data using text
analysis techniques. Sentiment analysis allows businesses to identify
customer sentiment toward products, brands or services in online
conversations and feedback. Sentiment analysis models focus on
polarity (positive, negative, neutral) but also on feelings and emotions
(angry, happy, sad, etc), and even on intentions (e.g. interested v. not
interested). Sentiment analysis has become a hot topic and many big
companies are investing their resources to predict the results for their
businesses. The working principle of sentiment analysis includes
tokenization, word filtering, stemming and classifications. In
tokenization, text needs to be segmented into units such as words/
numbers or punctuations. Next step stemming which is the process of
removing prefixes and affixes to convert a particular word into its
stem. After preprocessing, we analyze the dataset by performing
classification using Naïve Bayes, Support Vector Machine and Logistic
Regression. Here, we determine the best model based on accuracy.
Hence, We analyze and study the features that affect the scores of our
review text and finally classify the movie as positive or negative.
Huge textual data is available on sites like Amazon, IMDB, Rotten
Tomatoes on movies and analyzing such massive data manually is a
tedious task. So, to speed up the process, programmers use certain
techniques to extract out public opinion. One of which is using
sentiment analysis. Sentiment analysis is a submodule of opinion
mining where the analysis focuses on the extraction of text and
opinions of the people on a particular topic. We are making use of
IMDB reviews on movies to predict how the users have rated the
movies and predict the movies that have a positive or negative review.
We proposed a model that includes different sentiment analysis
methods which will help us to extract useful information from the data
and predict which is the most suitable classifier for this particular
domain by looking at accuracy. Models like Naïve Bayes, Support
Vector Machine and Logistic regressions. Due to the lack of strong
grammatical formats in movie reviews which is an informal jargon we
also take into account the N-Grams and count vectorizer approach.
Tokenization is used to transfer the input string into a word vector,
stemming is used for extracting the root of the words, while feature
selection fetches the essential word and lastly classification is used to
classify the movie as positive or negative.
Methodology
In our experiment we will made use of Naïve Bayes, Logistic
Regression, and Support Vector Machine. We will trained our model
on the above classifiers to predict the movie polarity as positive or
negative
Naïve Bayes: It is a classification algorithm, primarily used for text
classification involving high dimensional training data sets. Example
spam filtering, sentiment analysis etc. This algorithm learns the
probability of an object with certain features belonging to a particular
class.

Logistic Regression: Logistic regression is quite similar to linear


regression but here, instead of fitting a line to our data we try to fit ‘S’
shaped logistic function(Sigmoid Function).
Support Vector Machine: SVM is a regression and classification
algorithm. It constructs a hyperplane or set of hyperplanes in infinite
dimensional space to do the classifications. It looks at the extremes of
the data set and draws a decision boundar (Hyperplane). SVM is
known for its good performance
Refrences
[1]. MaisYasen, Sara Tedmori. “Movies Reviews Sentiment Analysis
and Classification”. IEEE Jordon International Joint Conference on
Electrical Engineering and Information Technology (JEEIT). 978-1-
5386-7942-5.
[2]. Tirath Prasad Sahu, Sanjeev Ahuja. “Sentiment Analysis of movie
reviews: A study on feature selection and classification algorithms”.
International Conference on Microelectronics, Computing, and
Communication (MicroCom).978-1-4673-6621-2.
[3]. Wijayanto, Unggul and Sarno, Ritanarto. “An Experimental Study
of Supervised Sentiment Analysis Using Gaussian Naïve Bayes”. 476-
481.10.1109/ISEMANTIC.2018.8549788.
[4]. Tejaswini M. Untawale, G. Choudhari. “Implementation of
Sentiment Classification of Movie Reviews by Supervised Machine
Learning Approaches”. 978-1-5386-7808-4.
[5]. Sourav Mehra, Tanupriya Choudhary. “Sentiment Analysis of
User Entered Text”. International Conference of Computational
Techniques, Electronics and Mechanical Systems (CTEMS). 978-1-
5386-7709-4.
[6]. Nisha Rathee, Nikita Joshi, Jaspreet Kaur. “Sentiment Analysis
Using Machine Learning Techniques on Python”. 978-1-5386-2842-3
“https://ieeexplore.ieee.org/document/8663224”.

You might also like