Scribd
Upload
6 views11 pages

Sentiment Analysis

Uploaded by

Karthick-5018-IT
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
6 views11 pages

Sentiment Analysis

Uploaded by

Karthick-5018-IT
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

MAHENDRA INSTITUTE OF TECHNOLOGY

(AUTONOMOUS)
DEPARTMENT OF INFORMATION TECHNOLOGY

SENTIMENTAL ANALYSIS ON TWITTER DATASET USING MACHINE


LEARNING ALGORITHM

0th REVIEW-DATE-23/01/2022
PRESENTED BY:

1. VASUNTHARA.D (319UIT055) GUIDED BY:


2. JANANI.R (319UIT016)
MR.K.SATHYASEELAN
3. PRIYA.V (319UIT039) AP/IT
4. JANANI ISHWARYA.S (319UIT015)
OBJECTIVE

Sentiment Analysis is a task to identify an text as


comments, reviews or message.
To implement an algorithm for automatic classification
of text into positive, negative, neutral, or negation.

2
Abstract

▪ Sentiment Analysis or Opinion Mining is one of the major tasks


of Natural language Processing.
▪ In this the data's are extracted from Twitter dataset.
▪ To tackle Sentiment Polarity Categorization.
▪ Sentiment Polarity Categorization is Sentence level and review
level categorization.

3
Existing System

▪ For the Review based categorizing the Support Vector


Machine is used since it gives the best accuracy of
sentiments.
▪ It is a method for the classification of both linear and
nonlinear data.
▪ The SVM searches for the linear optimal separating hyper
plane (the linear kernel), which is a decision boundary that
separates data of one class from another.
▪ If the data is linearly inseparable, the SVM uses nonlinear
mapping to transform the data into a higher dimension.
▪ It then solve the problem by finding a linear hyper plane.
4
DISADVANTAGE

▪ Biased reviews.
▪ Subtlety.
▪ Thwarted Expectation.
▪ Ordering effects.
▪ Aspects or attributes finding.
▪ Difficult interpretation of resulting model.

5
PROPOSED SYSTEM

▪ In this, the Sentence level Categorizer is used for collecting the


datasets from Twitter.
▪ The datasets are then tokenized by TOKENIZER.
▪ The tokens are then processed by DATA PRE-PROCESSING i.e. Data
cleaning, Data Integrity, Data Transformation and Reduction is
carried out to an understandable format this is then implied to an
identifier for identifying whether the given datas are positive,
negative, neutral, or negation.
▪ Machine Learning algorithm is to classify the datasets since it is the
best classifier for Sentence Level Categorization.
▪ By the Machine Learning algorithm the classified datas are
visualized by python

6
Advantage

▪ Model is easy to interpret.


▪ Can be Domain-Specific.
▪ Can be more Robust.
▪ Efficient computation.

7
Hardware Used

Processor: above i3 processor


RAM: 8GB
Harddisk:1TB

8
Software used

Operating System: Windows10


Language:PYTHON3.10
Tool: Anaconda Navigator

9
Architecture Diagram

10
References

▪ [1] S. Aliza, C. Nadam, and S. Basr,. "Twitter sentiment


analysis." In Proceedings of the 6th International
conference on Information Technology and Multimedia,
pp. 212-216. IEEE, 2014.
▪ [2] COVID-19 pandemic in India. Wikipedia. Retrieved
June 22, 2020, from
https://en.wikipedia.org/wiki/COVID-19_pandemic_in_India
.
▪ [3] J. Samuel, G. G. Ali, Md Rahman, Ek Esawi, and Yana
Samuel, "Covid-19 public sentiment insights and machine
learning for tweets classification.", Information, vol. 11,
no. 6, pp. 314, 2020.
11

You might also like