Authors :
Shravani Sanjyot Shete
Volume/Issue :
Volume 7 - 2022, Issue 6 - June
Google Scholar :
https://bit.ly/3IIfn9N
Scribd :
https://bit.ly/3IU9Nm9
DOI :
https://doi.org/10.5281/zenodo.6867549
Abstract :
Here in this project the main goal is to gain
access to the social media platform posts, here we use
Twitter. The most important asset here is the tweets that
users post using their account. Using the Tweepy library
in Python we extract these tweets using a get request and
perform sentiment analysis on them. This is a classic
example of using artificial intelligence for data analysis.
Theory understands whether a tweet is categorized into a
positive or negative category. The main intention here is
to identify the crowd emotion using this method. This
solution can be used in various fields and applications to
gain a large scale input on an ongoing topic. We are using
social media platforms such as it is one of the most used
platforms.
Using sentimental analysis and hashtags we are able
to gauge the sentiment behind the tweet. To analyze the
tweets we are using the following libraries, TextBlob - this
is used to keep processed the textual data gain from this
live data set from Twitter.
For the implementation of the project we have gone
through various approaches with different types of
dataset such as hashtagged dataset, Emoticon dataset,
Positive and Negative dataset. After the pre-processing of
these datasets we calculate the accuracy and check which
among the following gives us the maximum accuracy and
we continue to use those methods for the further
classification of our extracted features.
Keywords :
Artificial Intelligence, Twitter API, Sentimental Analysis, Textblob Library, Data Set, Vader Sentiment, Accuracy.
Here in this project the main goal is to gain
access to the social media platform posts, here we use
Twitter. The most important asset here is the tweets that
users post using their account. Using the Tweepy library
in Python we extract these tweets using a get request and
perform sentiment analysis on them. This is a classic
example of using artificial intelligence for data analysis.
Theory understands whether a tweet is categorized into a
positive or negative category. The main intention here is
to identify the crowd emotion using this method. This
solution can be used in various fields and applications to
gain a large scale input on an ongoing topic. We are using
social media platforms such as it is one of the most used
platforms.
Using sentimental analysis and hashtags we are able
to gauge the sentiment behind the tweet. To analyze the
tweets we are using the following libraries, TextBlob - this
is used to keep processed the textual data gain from this
live data set from Twitter.
For the implementation of the project we have gone
through various approaches with different types of
dataset such as hashtagged dataset, Emoticon dataset,
Positive and Negative dataset. After the pre-processing of
these datasets we calculate the accuracy and check which
among the following gives us the maximum accuracy and
we continue to use those methods for the further
classification of our extracted features.
Keywords :
Artificial Intelligence, Twitter API, Sentimental Analysis, Textblob Library, Data Set, Vader Sentiment, Accuracy.
