Authors :
Terisri Paladugula; Hiranmayee Nandyala; S V V S S C Ekantha; Puthin Dungala; Karteek Kishor Ambati; Jyothi Tanmai Ramisetti
Volume/Issue :
Volume 8 - 2023, Issue 12 - December
Google Scholar :
https://tinyurl.com/e25p6j68
Scribd :
https://tinyurl.com/44sbfetj
DOI :
https://doi.org/10.5281/zenodo.10401483
Abstract :
Sentiment analysis is a subset of text analysis
techniques that uses automatic text polarity detection.
One of the main responsibilities of NLP (Natural
Language Processing) is sentiment analysis, often known
as opinion mining. In recent years, sentiment analysis
has gained a lot of popularity. It is meant for people to
build a system that can recognize and categorize
sentiment or opinion as it is expressed in an electronic
text. Nowadays, people who wish to purchase consumer
goods prefer to read user reviews and participate in
public online forums where others discuss the product.
This is because consumers frequently have to make
trade-offs when making purchases. Before making a
purchase, a lot of customers read other people's reviews.
Individuals frequently voice their opinions about several
things. Opinion mining has grown in significance as a
result. Sentiment analysis is the process of determining if
the expressed opinion about the subject is favorable or
negative. Customers must choose which portion of the
available data to utilize. Sentiment analysis is the
technique of locating and removing subjective
information from unprocessed data. If we could
accurately forecast sentiments, we could be able to
gather online opinions and anticipate the preferences of
online customers. This information could be useful for
study in marketing or economics. As of right now,
sentiment classification, feature-based classification, and
handling negations are the three main issues facing this
research community.
Keywords :
Numpy, Pandas, TF-IDF, Tfidf Vectorizer, Linear SVC, Train-Test Split, Accuracy Score, Classification Report, Confusion Matrix, user Input, Vectorization, Prediction, Preprocessing, Text Classification, Supervised Learning, Machine Learning Model, Scikit-Learn.
Sentiment analysis is a subset of text analysis
techniques that uses automatic text polarity detection.
One of the main responsibilities of NLP (Natural
Language Processing) is sentiment analysis, often known
as opinion mining. In recent years, sentiment analysis
has gained a lot of popularity. It is meant for people to
build a system that can recognize and categorize
sentiment or opinion as it is expressed in an electronic
text. Nowadays, people who wish to purchase consumer
goods prefer to read user reviews and participate in
public online forums where others discuss the product.
This is because consumers frequently have to make
trade-offs when making purchases. Before making a
purchase, a lot of customers read other people's reviews.
Individuals frequently voice their opinions about several
things. Opinion mining has grown in significance as a
result. Sentiment analysis is the process of determining if
the expressed opinion about the subject is favorable or
negative. Customers must choose which portion of the
available data to utilize. Sentiment analysis is the
technique of locating and removing subjective
information from unprocessed data. If we could
accurately forecast sentiments, we could be able to
gather online opinions and anticipate the preferences of
online customers. This information could be useful for
study in marketing or economics. As of right now,
sentiment classification, feature-based classification, and
handling negations are the three main issues facing this
research community.
Keywords :
Numpy, Pandas, TF-IDF, Tfidf Vectorizer, Linear SVC, Train-Test Split, Accuracy Score, Classification Report, Confusion Matrix, user Input, Vectorization, Prediction, Preprocessing, Text Classification, Supervised Learning, Machine Learning Model, Scikit-Learn.