Professional Documents
Culture Documents
We would like to express our special thanks of gratitude to Deputy Director Sunil Sharma
for all his technical support and help in this project, as well as our Program Director Krishna
Prasad Acharya and Head of Department Ridip Khanal who allowed this project topic and
gave us this golden opportunity to do this wonderful project on the topic ‘Sentiment Based
Movie Rating System’, which also helped us in doing a lot of Research and we came to know
about so many new things that regular academics would have never taught. We are really
thankful to them for all their support, helps, guidance, motivations and corrections.
Secondly, we would also like to thank our parents and friends who helped us a lot in
finalizing this project within the limited time frame. Without all their help, we would have
never stepped into this project.
We appreciate all the technical support and motivation given by BCA program Mechi
Multiple Campus and all the helps provided in order to keep this project aligned with its
actual objectives.
Abstract
Sentiment based Movie Rating System is a online web application where a users comments
on a particular movie and based on those comments system generates the ratings to the
particular movies. It allows for the automated movie rating system. In the present scenario,
rating of a movies is given by media personnel which is not influenced by a users true
emotions and also leads to the false ratings. But in ‘Sentiments based Movie Rating System’
false rating cannot be entered since system calculates based on user comments. Thus,
'Sentiment Based Movie Rating System' removes human errors that commonly occur during
manual analysis and provides an unbiased result.
Contents
Acknowledgement.................................................................................................................................i
Abstract................................................................................................................................................ii
1. Introduction.................................................................................................................................1
2. Problem statement.......................................................................................................................1
3. Objective.......................................................................................................................................1
4. Methodology.................................................................................................................................2
5. Requirement Identification.........................................................................................................3
6. Feasibility Study..........................................................................................................................5
8. Algorithm.....................................................................................................................................7
9. Gantt Chart..................................................................................................................................8
10.2.1. ER Diagram................................................................................................................10
13.References.....................................................................................................................................13
List of figures
2. Problem statement
Rating of a movie should be done on basis of a user true feeling towards a movie.
However, in present context rating of a movie is given by media personnel and critics
which is not influenced by a users true emotions and also leads to a human error that
occurs during the manual analysis. Our System will provide a feature where user
comments on a movie and the system gives rating after analyzing the sentiments of
the user comments i.e it allows for the automated movie rating system. our system
provides an unbiased result and also excludes human efforts and saves time and
resources.
3. Objective
To provide users a platform for sharing their honest review about a movie that
the movie is worth to watch or not.
To generate automated rating in number between 0 to 5 of a particular movies
as per the user comments.
4. Methodology
As the requirements of the project are well understood and the features are clear we
propose to use the traditional waterfall approach to build our system. The project
timeline is fixed and the cost is limited. The scope of the project is also clear and well
known so the project team has decided to use the traditional waterfall model.
Requirement Analysis : In this phase all the requirements of the project are analyzed
and documented in a specified document and also feasibility analysis is done to check
if these requirement are valid. It is essential to consider any limitations and constraints
(e.g. time, budget constraints ) which can affect the development process.
System Design : In this phase, the system design is prepared which specifies
hardware and system requirements, such as data layers, programming languages,
network infrastructure, user interface.
Implementation : In this phase, the source code is written as per requirements. The
physical design specification are turned into a working code.
Testing : After the implementation the code is tested for all possible defects by
running test case either manually or by automation.
Deployment : In this phase, the software is deployed into a live environment ( client's
server ) in order to test its performance. Once the software is deployed, it becomes
available to end-users. Sometimes, this phase also includes training of real-time users
to communicate benefits of the system.
Maintenance: After the deployment phase, the step is to provide support and
maintenance for the software, making sure its runs smoothly. if the client and users
come across errors/defects/bugs during use, fixing them is the main purpose of the
stage.
5. Requirement Identification
5.1. Study of Existing System
The only existing system in this context is the media personnel movie rating
system where the media personnel give rating to a movie after watching and
also a normal user gives points/stars as a rating to a particular movie. Our
system provides a feature where user comments on a movie and based on
those comments rating is generated. our system generates the automated
ratings for a particular movie.
I. Pros of Existing System
The only advantage of existing system is that viewers' can decide whether the
movie is worth to watch or not and saves their time.
6. Feasibility Study
6.1. Technical Feasibility
The system is developed by using best technological system development
techniques such as OOPHP, JavaScript, JQuery, Bootstrap, CSS and MySQL
database without any problems. When we evaluate the hardware’s and software’s
requirement and how they meet the need of the proposed system, our proposed
system is technically feasible because we have used currently available and
affordable technologies to develop the proposed system with easy and attractive
user interface.
6.2. Operational Feasibility
The system is operationally feasible by changing the manual system to the web
based online system and giving the user easy to use automated system or takes
advantages of business opportunity by minimizing efforts and time.
6.3. Economical Feasibility
The development of this system in general case have no cost, since no components
or team members are getting paid or purchased. The project is the part of
academic qualification for Bachelor’s Degree in Computer Application Tribhuvan
University and there is no monetary factor involved. So the project is
economically feasible.
7. Working Mechanism of Proposed System
8. Algorithm
For the analysis of the sentiments we have decided to use KNN (Known Nearest
Neighbour) algorithm.
K-Nearest Neighbour is one of the simplest Machine Learning algorithms
based on Supervised Learning technique .
K-NN algorithm assumes the similarity between the new case/data and
available cases and put the new case into the category that is most similar to
the available categories.
K-NN algorithm stores all the available data and classifies a new data point
based on the similarity. This means when new data appears then it can be
easily classified into a well suite category by using K- NN algorithm.
K-NN algorithm can be used for Regression as well as for Classification but
mostly it is used for the Classification problems .
KNN algorithm at the training phase just stores the dataset and when it gets
new data, then it classifies that data into a category that is much similar to the
new data [6].
How does KNN algorithm works :
Step-4: Among these k neighbors, count the number of the data points in each category.
Step-5: Assign the new data points to that category for which the number of the neighbor
is maximum.
9. Gantt Chart
We have divided the project into the tasks and milestones as shown in figure:
Prabin Rajbanshi User Module Design user interface and user dashboard
Implement the algorithm for sentiment
analysis.
Documentation of the project.
13. Conclusion
Sentiment Based movie rating system aims at developing a website that manages the
reviews given to the movie and predicts the rating corresponding to each review. It
will show the overall rating of the movie which will change as soon as the movie
viewers enters a new review. Our proposed system will have two types of users,
registered or unregistered user. Unregistered user can view the trailer of movie and
can only read review of movie viewers. The registered user can view trailers give
review about the movie and see emotion of the movie viewers is displayed after
analysing the review given by him. Best and Worse reviews for particular movies are
shown. Genre, director, writer, movie stars and short summary of movie is shown for
movie viewers knowledge. The system also generate automatic rating in number up to
5 and also display top rating movie as per analysis.
13.References
[1] Grimes, "sentiment," unstructured data and 80 percent rule cMBRIDGE BRIDGEPOINTS, pp. 240-
250, 2008. [Accessed 27 03 2022].
[2] R. Feldem, The text mining handbook: Advanced approaches in analyzing unstructured data,
canbridge university press, 2007. [Accessed 24 03 2022].
[3] "Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing
(EMNLP 2002)," Association for Computational Linguistics, 2002, p. 79–86. [Accessed 27 03
2022].
[5] M. R. &. J. Gama, ""Marketing Research: The Role Of Sentiment Analysis,"," p. 489, 2013.
[Accessed 20 03 2022].