FRAMEWORK
FRAMEWORK
Social networking sites have become very popular. Millions of users conveniently express
their views and opinions on a wide array of topics. These users share a lot of information
about trending topics and current issues. Thus, these platforms generate a large amount of
data. Because of a free format of messages and an easy access to micro blogging platforms
there is a shift from traditional blogs to these services.
Sentiment analysis on the tweets collected is useful for knowing the public sentiments. But,
due to misspellings and slangs in the tweets; Twitter Sentiment Analysis is different from
general sentiment analysis.
INTRODUCTION
In the introduction, we discuss the importance of sentiment analysis in understanding how
people feel about different software engineering topics. The project aims to analyze social
media posts to determine the public's opinion about various software engineering trends and
technologies.
The Problem Statement will describe the need for this analysis in understanding public
sentiment.
The Objectives section outlines the goals of the project, The methodology involves collecting
posts using the Twitter API, cleaning and preprocessing the data, and then applying sentiment
analysis to classify the posts as positive, negative, or neutral. Afterward, We will evaluate the
model's performance.
Lastly, in the Organization section, we give a brief description of how the report is structured.
LITERATURE SURVEY
We review relevant papers and research in the Literature Survey section. This helps to
provide context and background for the work we are doing and highlights existing work in
sentiment analysis
SYSTEM DEVELOPMENT
System Development is where the core development of the system is covered. The Main
Classifier section focuses on the algorithm we’ll use to perform sentiment analysis.
The System Requirements section lists the technical specifications necessary to run the
system.
System Requirements :-
i) Hardware used:
Data Bus: 64-bit
Processor(CPU): Intel Core-i5(7th Gen)
8 GB RAM
ii) Software used:
OS: Windows 10
Python programming language 3.7
iii) Twitter Developer Account to access Twitter API
Next, in Model Development, we will describe the creation of the machine learning model
used for classification.
The Process Flow section will detail the overall steps taken to implement the project.
Finally, in Libraries Used, we’ll list the tools and libraries utilized to build the system.
IMPLEMENTATION STEPS
The implementation consists of collecting data from Twitter using relevant hashtags, cleaning
the text data, applying sentiment analysis, and then presenting the results through graphs and
charts.
PERFORMANCE ANALYSIS
the Performance Analysis section, we’ll explain how the system’s performance will be
evaluated.
The Test Plan section will outline the tests conducted to ensure the system works as
expected.
the Classification section focuses on how accurately the sentiment is classified into positive,
negative, or neutral.
CONCLUSION
We will conclude the report. The Conclusion section summarizes the findings from the
sentiment analysis, and in the Future Scope section, I will discuss potential improvements
and extensions for the project.
Lastly, We’ll mention some of the Applications of the sentiment analysis model and how it
can be used in real-world scenarios.