Sentimental Ana

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 5

Analyzing Consumer Opinions on Electric Vehicles: A Sentiment Analysis Perspective

Introduction

In this project, our objective is to conduct sentiment analysis on electric vehicle reviews
within the business improvement category. We will employ natural language processing
(NLP) techniques and machine learning algorithms to accurately classify each review as
positive, negative, or neutral."

Sentiment analysis aims to determine the attitude of a speaker or a writer with respect to
some topic or the overall contextual polarity of a review.

2 Why electric vehicles sentiment analysis?

Sentiment analysis on electric vehicles involves evaluating and understanding people's


opinions, attitudes, and emotions regarding electric vehicles (EVs). This analysis can be
performed on various sources of data, such as social media posts, online reviews, news
articles, and forums. The goal is to gain insights into how the general public or specific
groups perceive electric vehicles

4 Methodologies:

Data Collection:

Gather a dataset of social media posts, customer reviews, news articles, or any other
text data that contains opinions or sentiments.

Tokenization:

This electric vehicle is really good!

Tokenization

 This
 Electric
 vehicle
 is
 really
 good
 !

Cleaning the data :

This electric vehicle is really good!

Remove the special characters

 This
 Electric
 vehicle
 is
 really
 good

Removing stop words:

This electric vehicle is really good!

Remove the stop word

 This
 Electric
 vehicle
 is
 really
 Good

Classification:

This electric vehicle is really good!


Positive: +1

Negative:-1

Neutral: 0

 This
 Electric +/-
 vehicle
 is Classify them as positive,negative and neutal
 really Eg: This electric vehicle is really good!
 Good +/-
 !

Apply Supervised This electric vehicle is really good!

Algorithm for Classification: Positive: +1

Negative:-1

Neutral: 0

This Train your model with


electric 0 bag of words or lexicons,
vehicle and test it on the
is analysing statement
really
good! More the accuracy
+1 score better will be the
classification
Calculation

Positive: +1

Negative:-1

Neutral: 0

This +1+0=1
electric 0 since ,the polarity is greater
vehicle than 0 so the given
is statement is positive
really 1
good!
5 Graph/analysis/simulation:

Pie Chart

Reviews
Neutral
17%

Positive
50%

Negative
33%

6 Results & discussion

7 Conclusion and future work

8 references

2. Business: companies use it for improving business plans, to determine customers’fellings about
products or brands to see how people react to their compaigns or product releases and to figure
why those products aren’t selling.

Problem statement, Objectives

Problem statement: There are many tools like Enginuity,steamcrab,meaningcloud, social mention,R
and python.There are many algorithms as well like SVM, naiveBayes which are used in natural
language processing to predict the polarity on sentimental analysis.

Objectives:

Importing modules and load the data :

Pie chart of classification :


Creating word cloud

wc=WordCloud(background_colour=”white”

mask=mask,maxwords=3000,stopwords=stopwords,repeat=True)

word cloud for negative class images is as below:

project lifecycle:

data preparation
data cleaning
exploratory data analysis
language models
model evaluation

You might also like