VISVESVARAYA TECHNOLOGICAL UNIVERSITY

SOCIAL MEDIA ASSISTING PLATFORM USING

SENTIMENT ANALYSIS
PROJECT REPORT
Submitted by

SURYA K M 1RF20IS054
SWATI VINAYAK BHAT 1RF20IS056
PRAVEEN PATIL 1RF20IS038
ANTHONY SHASHANTH 1RF20IS009

Under the Guidance of

Dr.Kiran Kumar,
Associate Professor,
ISE Department, RV Institute of Technology and Management

in partial fulfillment for the award of degree

of

Bachelor of Engineering
IN
Information Science and Engineering
RV INSTITUTE OF TECHNOLOGY AND MANAGEMENT,
BANGALORE-560076
2023-24
 RV INSTITUTE OF TECHNOLOGY AND MANAGEMENT, BANGALORE - 560076
(Affiliated to VTU, Belgaum)

DEPARTMENT OF INFORMATION SCIENCE AND ENGINEERING

CERTIFICATE

Certified that the project work titled “Social Media assisting platform using Sentimental
Analysis” is carried out by SURYA K M (1RF20IS054), SWATI VINAYAK BHAT
(1RF20IS056), PRAVEEN PATIL (1RF20IS038) and ANTHONY SHASHANTH
(1RF20IS009) who are Bonafede students of RV Institute of Technology and Management,
Bangalore, in partial fulfillment for the award of degree of Bachelor of Engineering in
Information Science and Engineering of the Visvesvaraya Technological University, Belgaum
during the year 2020-2024. It is certified that all corrections/suggestions indicated for the internal
Assessment have been incorporated in the report deposited in the departmental library. The
project report has been approved as it satisfies the academic requirements in respect of project
work prescribed by the institution for the said degree.

Signature of Guide: Signature of Head of the Department: Signature of Principal:

External Viva

Name of Examiners
RV INSTITUTE OF TECHNOLOGY AND MANAGEMENT, BANGALORE - 560059
(Affiliated to VTU, Belgaum)

DEPARTMENT OF INFORMATION SCIENCE AND ENGINEERING

DECLARATION

We, SURYA K M (1RF20IS054), SWATI VINAYAK BHAT (1RF20IS056), PRAVEEN

PATIL (1RF20IS038), ANTHONY SHASHANTH (1RF20IS009), the students of seventh
semester B.E., Information Science and Engineering, hereby declare that the project titled
“Social Media assisting platform using Sentimental Analysis” has been carried out by us and
submitted in partial fulfillment for the award of degree of Bachelor of Engineering in
Information Science and Engineering. We do declare that this work is not carried out by any
other students for the award of a degree in any other branch.

Place: Bangalore Signature

Date: 1. SURYA K M
2. SWATI VINAYAK BHAT
3. PRAVEEN PATIL
4. ANTHONY SHASHANTH
 ABSTRACT
The following report is a compilation of final year project work that tracks the project's overall
progress. The introduction, background information, development progress documents, project
outcome, and future possible engagement are all included in this report. The research culminates in
a fully functional mobile application that performs sentiment analysis on YouTube comments,
tweets, and custom texts. Spam and sarcasm detection are also included for a more reliable analysis.
Being a social media assisting platform, there is also a feature for connecting job seekers with
providers. This project employs a Multinomial Naive Bayes Probabilistic Classifier. Flutter and
Flask are utilized to create a user-friendly application. The project's backend API is hosted on the
Heroku platform.
 ACKNOWLEDGEMENT

The satisfaction and the euphoria that accompany the successful completion of any task
would be incomplete without the mention of the people who made it possible. The constant
guidance of these people and encouragement crowned our efforts with success and glory.
Although it is not possible to thank all the members who helped with the completion of
phase 1 of the project individually, we take this opportunity to express our gratitude to one
and all.

We would like to thank the VTU, Belagavi, for having this project work as part of its
curriculum, which gave us a wonderful opportunity to work on our research and
presentation abilities.

We express our sincere gratitude to Dr. Jayapal R, Principal, R V Institute of Technology

and Management for the support and encouragement.

We wish to place on record our grateful thanks to Dr. Latha C A, Professor & HOD,
Department of ISE, R V Institute of Technology and Management, for the constant
encouragement provided to us.

We are indebted with a deep sense of gratitude for the constant inspiration, encouragement,
timely guidance, and valid suggestions given to us by our guide Dr. Kiran Kumar,
Associate Professor, Department of ISE, R V Institute of Technology and Management.

We are thankful to the Project Coordinator and all the staff members of the department for
providing relevant information and helping in different capacities in carrying out this phase
-1 project.

Last, but not least, we owe our debts to our parents, friends and also those who directly or
indirectly have helped us to make the phase - 1 project work a success.
 TABLE OF CONTENTS

Chapter
PARTICULARS Page. No
No.

Abstract i

Acknowledgement ii

1 Introduction 1

1.1 Problem Statement 1

1.2 Scope and Motivation 2

1.3 Objective
1.4 Methodology
1.5 Overview of the Report
2 Literature Survey 3

2.1 System Study 3

2.2 Proposed work 5

3 System Requirement Specification 8

3.1 Functional Requirements 8

3.2 Non-Functional Requirements 8

3.3 Hardware Requirements 9

3.4 Software Requirements 9

4 System Design 11

4.1 Design Overview 11

 4.2 System Architecture 12

4.3 Data Flow Diagram 13

4.4 Use Case Diagram 14

5 Conclusion 16

Reference 17
Social Media assisting platform using Sentimental Analysis

CHAPTER 1

INTRODUCTION
In the age of digital communication and social media, the influence of online platforms has
become ubiquitous, impacting both personal and professional spheres of life. This project
addresses the growing need for a tool that assists individuals in navigating the social media
landscape, specifically targeting professionals who engage with social media in their career
pursuits. This platform is designed to be a comprehensive solution, integrating sentiment analysis
features to empower users with insights into the emotional tone of online conversations.

This Project is a mobile application crafted using a modern technology stack, combining the
versatility of Flutter for the front end and Flask for the back end. Leveraging the power of
Multinomial Naive Bayes Theorem, the algorithmic backbone of this project provides users with
a sophisticated sentiment analysis capability.The primary focus of this project is to cater to
individuals involved in social media-related professions, such as recruiters and job seekers. By
enabling users to perform sentiment analysis on YouTube video comments and tweets, This
Project equips professionals with a valuable tool to gauge the public perception and sentiment
surrounding specific content. This not only facilitates a deeper understanding of audience
reactions but also streamlines the recruitment process by fostering connections between social
media professionals.

The significance of This Project lies in its potential to enhance the efficiency and effectiveness of
social media interactions for professionals. As social media continues to play a pivotal role in
shaping professional networks and career opportunities, This Project emerges as a timely and
relevant solution. The subsequent sections of this project report will delve into the technical
aspects of the application, detailing the architecture, functionalities, and the implementation of
the Multinomial Naive Bayes algorithm. Additionally, the report will provide insights into the
challenges faced during the development process and the strategies employed to overcome them,
offering a comprehensive overview of the project.

Department of Information Science and Engineering

1
Social Media assisting platform using Sentimental Analysis

1.1 PROBLEM STATEMENT

The challenge is the lack of a user-friendly, real-time sentiment analysis tool for social media
comments and tweets, hindering individuals and organizations from effectively understanding
and utilizing the sentiments expressed in online conversations. This statement succinctly
highlights the core problem our project aims to solve.

1.2 SCOPE AND MOTIVATION

The platform is a tool for professionals who are engaged in multiple forms of social media works
like content creators, freelancers, marketing personals, etc. The solutions that we have come up
with to the previously stated challenges are as follows:
i. To keep track of audience feedback, content providers can't look through every single comment
on their YouTube videos. This takes a long time and is frequently unfeasible. The Sentiment
platform may be used to scan comments in bulk and content creators can be provided with a
summary feedback report.
ii. Not every company or workforce can afford the expensive cost of a data science team, the
platform can be utilized by marketing and advertising agencies to find what people are saying to
particular things. At this stage of prototype level, YouTube comments and Twitter tweets are
available as means of data.
iii. Freelancers related to social media work can be connected with relevant work vacancies in
the platform. We considered this feature to solve the second problem we mentioned in the
previous heading.
iv.Political Campaigns or similar events have their own objectives. To monitor what people are
saying about the particular event can be monitored from the platform using tweets sentiment
analysis to specific hashtag/topic.

Department of Information Science and Engineering

2
Social Media assisting platform using Sentimental Analysis

1.3 OBJECTIVES

1. Develop a User-Friendly Mobile Application: Design and implement a mobile

application with an intuitive and user-friendly interface using Flutter for the front end.
The application should cater specifically to professionals engaged in social media,
ensuring ease of navigation and accessibility of key features.
2. Integrate Sentiment Analysis Features: Incorporate sentiment analysis functionalities
into the mobile application to allow users to analyze sentiments in YouTube video
comments and tweets. Utilize the Multinomial Naive Bayes Theorem as the algorithmic
foundation for sentiment analysis, ensuring accurate and meaningful insights into the
emotional tone of online conversations.
3. Facilitate Professional Connections: Create a platform that fosters connections between
social media-related job recruiters and job seekers. Enable users to leverage sentiment
analysis results to enhance their professional interactions on social media, thereby
promoting networking and recruitment opportunities within the social media landscape.
4. Ensure Robust Back-End Functionality: Develop a robust back-end system using
Flask to support the seamless functioning of the mobile application. Implement features
such as data storage, retrieval, and real-time analysis, ensuring the reliability and
efficiency of the overall system. Address security and privacy concerns associated with
social media data to build trust among users.

1.4 METHODOLOGY
Considered Methodologies: Waterfall : It is a linear and traditional approach of software
development. Each phase of process is carried out in sequential order. Next task is not executed
without finishing the previous one (Young, 2013).
Selected Methodology: The Scrum framework of agile methodology will be utilized for this
project because it is appropriate for this project type. Agile characteristics such as flexible work
divisions for individuals, working software over exhaustive documentation, and adapting to

Department of Information Science and Engineering

3
Social Media assisting platform using Sentimental Analysis

changes are all part of the Scrum methodology. Each sprint of the scrum is dedicated to
completing specific tasks.
Phases of methodology

Scrum phases of Agile methodology are as follows:

i. Product Backlog Creation The functional and non-functional requirements, as well as product
features, are recorded at this phase for later implementation. The task description provided by the
client is broken down into smaller technical components to complete. The product owner or
client party meets with the scrum master to discuss the product's development. This engagement
can happen at any time during the development process.

ii. Sprint planning and Backlog creation The set of product backlog items are selected for the
next sprint in this phase. Usually, a sprint lasts about two weeks, the short duration sprints
provide the opportunity to accept client’s further feedback. This provides enough time to adapt
new changes if required. There is an additional benefit of extra time for bug addressing and
debugging. After breaking down the problem domains of the sprint into smaller tasks, the scrum
team is also responsible for prioritizing the work (Star Agile, 2020).
iii. Working on sprint/ Daily Scrum Following the planning and appropriate coordination, this is
the actual working stage on the product. A task progress board is kept up to date. Task cards are
divided into four categories: tasks to accomplish, current tasks, tasks to review, and completed
tasks.
iv. Sprint review or testing and product demonstration This phase is about viewing the tasks done
in this sprint. The quality of the sprint or deployment is evaluated and judged if any necessary
changes are essential to make. The product owner describes what product backlog items have
been ‘done’ and what not. The entire team collaborates on what to do next (Khristich, 2020).
v. Sprint retrospective It is a final meeting and last phase of the scrum development process. It is
attended by product owner/client, scrum master and development team. This is time-boxed for
forty five minutes a week (Khristich, 2020).

Department of Information Science and Engineering

4
Social Media assisting platform using Sentimental Analysis

CHAPTER 2
LITERATURE SURVEY
2.1 SYSTEM STUDY
The system study of a Social Media Assisting Platform employing Sentiment Analysis involves a
meticulous examination of its various components and processes. At the outset, a clear
articulation of the platform's objective is essential, delineating its purpose in providing assistance
through the analysis of sentiments expressed in social media posts. Understanding the needs of
the target users is paramount, paving the way for the identification of specific requirements that
the platform must address. Data collection methods, encompassing sources such as Twitter,
Facebook, or Instagram, necessitate careful consideration, with an emphasis on preprocessing
techniques to cleanse and normalize the data. The selection and implementation of an appropriate
Sentiment Analysis model, be it a machine learning algorithm or a deep learning model, play a
pivotal role in accurately categorizing sentiments within the social media content. Integration
with social media APIs, user-friendly interface design, and real-time sentiment display are
crucial for seamless user interaction. To maintain the integrity of the platform, a feedback
mechanism for users, security measures, scalability considerations, and ethical compliance are
imperative. Continuous monitoring, maintenance plans, legal adherence, and comprehensive
documentation further contribute to the development of a robust and effective Social Media
Assisting Platform.

Department of Information Science and Engineering

5
Social Media assisting platform using Sentimental Analysis

2.2 PROPOSED WORK

1. Mobile Application Development:

● Utilize Flutter for a cross-platform application.

● Create an intuitive and user-friendly interface for professionals.

2. Sentiment Analysis Algorithm:

● Implement the Multinomial Naive Bayes Theorem for accurate sentiment analysis.
● Train the system on a curated dataset to enhance accuracy.

3. Back-End Development:

● Deploy a robust Flask back end for data storage and real-time analysis.
● Ensure security measures to protect user data and privacy.

4. Real-Time Analysis and Professional Networking:

● Provide real-time sentiment analysis of YouTube video comments and tweets.

● Facilitate professional networking based on shared sentiments and interests.

2.3 SCOPE OF THE PROJECT

The scope of this project is multifaceted, aiming to develop a sophisticated social media assisting
platform tailored for professionals navigating the dynamic landscape of social media. The
primary focus is on creating a cross-platform mobile application using Flutter, ensuring
accessibility across diverse devices. This application will serve as an intuitive interface for
professionals engaged in social media-related activities. The core functionality lies in the
implementation of the Multinomial Naive Bayes Theorem for real-time sentiment analysis of
YouTube video comments and tweets, providing users with nuanced insights into the emotional

Department of Information Science and Engineering

6
Social Media assisting platform using Sentimental Analysis

tone of online conversations.

The back-end infrastructure, powered by Flask, will play a pivotal role in supporting the system's
functionality. It will be designed to handle data storage, retrieval, and real-time analysis, with a
particular emphasis on scalability and robust security measures. User authentication features will
be integrated to safeguard user data and ensure a secure platform.

Beyond sentiment analysis, the project aims to facilitate professional connections within the
social media domain. Users will be able to connect with like-minded professionals based on
shared sentiments and interests, enhancing networking opportunities. The development will
include a user-friendly graphical interface, real-time reporting features, and visualizations to
empower professionals in interpreting sentiment analysis results effectively.

Comprehensive testing procedures and optimization efforts will be undertaken to ensure the
reliability and efficiency of the entire system. Additionally, detailed documentation will be
provided to guide users on system usage, configuration, and maintenance. Through these
endeavors, the project aspires to deliver a comprehensive and impactful social media assisting
platform, contributing to the enhanced experiences of professionals within the social media
landscape.

Department of Information Science and Engineering

7
Social Media assisting platform using Sentimental Analysis

CHAPTER 3

SYSTEM REQUIREMENT SPECIFICATION

3.1 Functional Requirements:

1. User Authentication:
○ Users should be able to create accounts and log in securely to access the
platform's features.
2. Sentiment Analysis:
○ Implement sentiment analysis functionality to analyze YouTube video comments
and tweets in real-time.
○ Classify sentiments into categories such as positive, negative, or neutral.
3. Real-Time Reporting:
○ Provide users with real-time reports and visualizations of sentiment analysis
results.
○ Include graphical representations to enhance user understanding.
4. Professional Networking:
○ Facilitate connections between social media-related job recruiters and job seekers
based on shared sentiments and interests.
○ Include features for users to build and manage professional networks.
5. User-Friendly Interface:
○ Develop an intuitive and visually appealing graphical user interface (GUI) for the
mobile application.
○ Ensure easy navigation and accessibility for professionals with varying levels of
technological proficiency.
6. Back-End Functionality:
○ Implement a robust back-end system using Flask for data storage, retrieval, and

Department of Information Science and Engineering

8
Social Media assisting platform using Sentimental Analysis

real-time analysis.
○ Ensure scalability to accommodate a growing user base and increasing data
volume.
7. Customization Settings:
○ Allow users to customize settings such as notification preferences, sentiment
analysis parameters, and personal profiles.
8. Security Measures:
○ Incorporate robust security measures to protect user data and maintain privacy.
○ Implement encryption protocols for secure data transmission.

3.2 Non-Functional Requirements:

1. Performance:
○ The system should provide efficient sentiment analysis results in real-time,
ensuring minimal latency.
○ The application should be responsive, handling simultaneous user requests
effectively.
2. Scalability:
○ The system should be scalable to accommodate a growing user base and
increasing data volume without compromising performance.
3. Reliability:
○ The platform should be reliable, with a minimal occurrence of system failures or
disruptions.
○ Implement mechanisms for data backup and recovery.
4. Usability:
○ The user interface should be user-friendly, catering to professionals with varying
levels of technological proficiency.
○ Conduct usability testing to ensure a positive user experience.
5. Compatibility:
○ Ensure cross-platform compatibility of the mobile application, making it
accessible on both iOS and Android devices.

Department of Information Science and Engineering

9
Social Media assisting platform using Sentimental Analysis

○ The application should be compatible with popular web browsers for potential
future expansion.
6. Security and Privacy:
○ The system should adhere to industry-standard security practices to protect
against data breaches.
○ User authentication and authorization processes should be secure and robust.
7. Documentation:
○ Provide comprehensive documentation for users, including user guides, system
configurations, and maintenance procedures.
○ Maintain up-to-date documentation to facilitate ongoing system management and
updates.

3.3 Hardware Requirements:

1. Mobile Devices:
○ Compatible with iOS and Android devices.
○ Minimum RAM: 2GB.
○ Minimum Storage: 16GB.
2. Server Infrastructure:
○ Sufficient processing power for real-time sentiment analysis.
○ Adequate storage capacity for data storage and retrieval.
○ Reliable network connectivity for seamless data transfer.
3. Network Infrastructure:
○ High-speed internet connectivity for real-time analysis and data transfer.
○ Secure networking protocols to protect data during transmission.
4. User Workstations:
○ Standard computing devices with web browser compatibility for accessing the
platform.
○ Minimum RAM: 4GB.

Department of Information Science and Engineering

10
Social Media assisting platform using Sentimental Analysis

○ Minimum Storage: 256GB.

3.4 Software Requirements:

1. Operating Systems:
○ Mobile Application: Compatible with iOS 11 and above, Android 7.0 and above.
○ Server: Linux-based operating system (e.g., Ubuntu Server).
2. Development Frameworks:
○ Flutter for cross-platform mobile application development.
○ Flask for back-end development.
3. Database Management System:
○ PostgreSQL for robust data storage and retrieval.
4. Sentiment Analysis Algorithm:
○ Implementation of the Multinomial Naive Bayes Theorem for sentiment analysis.
○ Integration with Python for algorithmic implementation.
5. Web Browsers:
○ Compatibility with popular web browsers (e.g., Chrome, Firefox) for potential
web-based features.
6. Security Tools:
○ SSL/TLS for secure data transmission.
○ Encryption protocols for securing user data.
○ Firewall configurations to protect server infrastructure.
7. Integrated Development Environment (IDE):
○ Visual Studio Code or any preferred IDE for code development.
8. Version Control:
○ Git for version control and collaborative development.
9. Documentation Tools:
○ Markdown or any suitable documentation tool for creating user guides and system
documentation.

Department of Information Science and Engineering

11
Social Media assisting platform using Sentimental Analysis

10. Testing Frameworks:

○ Use testing frameworks like Pytest for backend testing.
○ Implement mobile application testing tools for frontend testing.
11. Containerization:
○ Docker for containerization, facilitating deployment and scalability.
12. Collaboration Tools:
○ Communication and collaboration tools (e.g., Slack, Microsoft Teams) for project
coordination.

CHAPTER 4
SYSTEM DESIGN

4.1 DESIGN OVERVIEW

The system design of the social media assisting platform is structured to provide a
comprehensive and efficient solution for professionals engaged in social media-related activities.
The design encompasses the architecture, components, and interactions within the system to
achieve seamless sentiment analysis, user networking, and an intuitive user experience.

1. Architecture:

The system adopts a client-server architecture, where the client is the cross-platform mobile
application developed using Flutter, and the server utilizes Flask for the back-end. The server
infrastructure includes a PostgreSQL database for robust data storage, retrieval, and real-time
analysis. This architecture ensures scalability, responsiveness, and facilitates real-time
communication between the mobile application and the back-end server.

Department of Information Science and Engineering

12
Social Media assisting platform using Sentimental Analysis

2. Sentiment Analysis Module:

The core of the system design is the sentiment analysis module, which employs the Multinomial
Naive Bayes Theorem for real-time sentiment classification. Implemented in Python, this module
analyzes YouTube video comments and tweets, categorizing sentiments into positive, negative,
or neutral. The accuracy of sentiment analysis is enhanced through continuous learning from a
curated dataset during the training phase.

3. User Networking Module:

The user networking module facilitates connections between social media-related job recruiters
and job seekers. It leverages shared sentiments and interests to create meaningful professional
connections. The module is integrated into the server infrastructure, providing a secure and
efficient platform for users to build and manage their professional networks.

4. Graphical User Interface (GUI):

The system design incorporates an intuitive and visually appealing GUI for the mobile
application. Developed using Flutter, the GUI ensures a seamless user experience, featuring
real-time reporting and visualizations of sentiment analysis results. Customization settings are
embedded within the GUI, allowing users to personalize their experience and access relevant
features easily.

5. Security Measures:

To ensure the security of user data and maintain privacy, the system design includes robust
security measures. SSL/TLS protocols secure data transmission, encryption techniques protect
user data, and firewall configurations safeguard the server infrastructure.

6. Scalability and Performance:

The system design prioritizes scalability to accommodate a growing user base and increasing
data volume. Performance optimization strategies are implemented to ensure minimal latency,
responsiveness, and efficient handling of simultaneous user requests.

Department of Information Science and Engineering

13
Social Media assisting platform using Sentimental Analysis

7. Documentation and Training:

Comprehensive documentation is integral to the system design, providing users with detailed
guides on system usage, configuration, and maintenance. Training materials are developed to
facilitate effective utilization of the platform's features, ensuring a positive user experience.

This system design overview lays the foundation for the subsequent phases of development,
implementation, and testing, ensuring that the social media assisting platform delivers a reliable,
efficient, and impactful solution for professionals navigating the social media landscape.

4.2 SYSTEM ARCHITECTURE

The architecture of the social media assisting platform is designed to be scalable, responsive, and
modular, ensuring efficient sentiment analysis, user networking, and a seamless user experience.
The system follows a client-server model, with the client represented by the cross-platform
mobile application and the server handling data processing, storage, and analysis.

1. Client-Side (Mobile Application):

● Front-End Framework: Developed using Flutter for cross-platform compatibility,

providing a uniform user experience on iOS and Android devices.
● User Interface (UI): Intuitive and visually appealing UI designed for ease of navigation,
featuring real-time reporting and visualizations of sentiment analysis results.
● Sentiment Analysis Integration: Implements client-side logic for interacting with the
server for sentiment analysis requests and displaying the results.

2. Server-Side (Back-End):

● Framework: Utilizes Flask, a lightweight Python web framework, for building the
back-end server.

Department of Information Science and Engineering

14
Social Media assisting platform using Sentimental Analysis

● Database Management: PostgreSQL is employed for data storage, retrieval, and

efficient management of user-related information and sentiment analysis results.
● Sentiment Analysis Module: Implements the Multinomial Naive Bayes Theorem for
sentiment analysis, continuously learning from a curated dataset for enhanced accuracy.
● User Networking Module: Facilitates connections between social media-related job
recruiters and job seekers based on shared sentiments and interests, ensuring secure and
efficient networking.

3. Security Layer:

● SSL/TLS Encryption: Secures data transmission between the mobile application and the
server, ensuring the confidentiality and integrity of user data.
● User Authentication: Implements secure user authentication measures to protect user
accounts and personal information.
● Firewall Configuration: Protects the server infrastructure from unauthorized access,
enhancing overall system security.

4. Scalability and Performance:

● Load Balancing: Utilizes load balancing mechanisms to distribute incoming requests

evenly, ensuring optimal utilization of server resources.
● Caching Strategies: Implements caching mechanisms to enhance system performance,
reducing response times for frequently accessed data.
● Database Indexing: Optimizes database queries with indexing to improve retrieval
speed, especially during real-time sentiment analysis.

5. Integration with External Services:

● Third-Party APIs: Integrates with external services for additional functionalities, such
as real-time content fetching or social media platform APIs for enhanced networking
capabilities.
● Containerization: Uses Docker for containerization, facilitating easy deployment,
scalability, and management of the system.

Department of Information Science and Engineering

15
Social Media assisting platform using Sentimental Analysis

6. Documentation and Logging:

● Comprehensive Documentation: Includes detailed documentation for users, developers,

and administrators, covering system usage, configuration, and maintenance procedures.
● Logging Mechanism: Implements logging to capture system events, errors, and user
activities for monitoring, debugging, and audit purposes.

Fig 4.1 System Architecture of Social Media Assisting platform

Department of Information Science and Engineering

16
Social Media assisting platform using Sentimental Analysis

4.3 DATA FLOW DIAGRAM

Fig 4.2 Data flow diagram of Social Media Assisting platform

Department of Information Science and Engineering

17
Social Media assisting platform using Sentimental Analysis

4.4 USE CASE DIAGRAM

A use case diagram in the Unified Modeling Language (UML) is a type of behavioral
diagram defined by and created from a Use-case analysis. Its purpose is to present a
graphical overview of the functionality provided by a system in terms of actors, their
goals represented as use cases), and any dependencies between those use cases. The main
purpose of a use case diagram is to show what system functions are performed for which
actor. Roles of the actors in the system can be depicted.

Fig 4.3 Use Case Diagram of Social Media Assisting platform

Department of Information Science and Engineering

18
Social Media assisting platform using Sentimental Analysis

CHAPTER 5
CONCLUSION
As we reach a pivotal juncture in the ongoing development of the social media assisting
platform, it is evident that our journey has been marked by significant strides in creating a tool
that holds immense promise for professionals navigating the social media landscape. The
foundations laid in the design and implementation phases have set the stage for a platform that
seeks to redefine how individuals engage with social media in their professional lives.

The sentiment analysis module, under continuous refinement, showcases early signs of its
potential to provide nuanced insights into the emotional nuances of online conversations.
Real-time reporting features and intuitive visualizations are evolving to empower professionals
with timely and meaningful information, enabling informed decision-making.

The ongoing development of the user networking module holds promise in fostering connections
among professionals within the social media domain. As this module evolves, it is anticipated to
become a catalyst for meaningful networking opportunities, contributing to the professional
growth and collaborative potential of our users.

The emphasis on security, scalability, and performance optimization remains at the forefront of
our development efforts. The integration of SSL/TLS encryption, user authentication measures,
and other security protocols ensures that user data remains safeguarded. Additionally, scalability
measures are being fine-tuned to meet the demands of a growing user base, while performance
optimization strategies are continuously refined to enhance the platform's efficiency.

The collaborative efforts of the development team, coupled with a commitment to industry best
practices, continue to drive the project forward. The journey ahead involves refining the existing
features, addressing emerging challenges, and incorporating user feedback to create a platform
that truly resonates with the needs of professionals in the dynamic realm of social media.

As we conclude this progress update, it is with anticipation and dedication that we look forward
to realizing the full potential of the social media assisting platform. The journey is ongoing, and
the commitment to delivering a transformative tool for professionals remains unwavering.

Department of Information Science and Engineering

19
Social Media assisting platform using Sentimental Analysis

REFERENCES

[1] A. Kaushik and S. Naithani, "A Study on Sentiment Analysis: Methods and
Tools", International journal of Science and Research, vol. 4, pp. 287-291, 2015.

[2] D. Jiang, Xiangfeng Luo, Junyu Xuan and Zheng Xu, "Sentiment computing for the
news event based on the social media Big Data", IEEE Access, pp. 1-6, 2016.

[3] M. Taboada, J. Brooke, M. Tofiloski, K. Voll and M. Stede, "Lexicon-based methods

for sentiment analysis", Comput. Linguistics, vol. 37, no. 2, pp. 267-307, 2011.

[4] Y. Rao, Q. Li, X. Mao and L. Wenyin, "Sentiment topic models for social emotion
mining", Information Sciences, vol. 266, 2014.

Department of Information Science and Engineering

20