Comparative Study of different algorithms in Sentiment Analysis on Twitter
Abstract & Details
Research Area
Machine Learning
Keywords
Sentiment analysis
Twitter
Data pre-processing
Feature extraction
training
testing
accuracy rate
Naïve Bayes
Support Vector Machine
Abstract
Today, understanding people’s concern is important in various domains. Lots of people express their feelings in various way on social media. Among people’s sentiment is very important because it has great impact on our society. For various purposes understanding the sentiment of people is important like business, elections and so on. For any business knowing the sentiment of people is important and it helps to grow it by taking some decisions on it. Organizations can make decisions about their many products when they get to know that what people think about their product that they are in support or in against. Social media is a very big platform where data can be collected. Twitter is a social media platform and millions of people uses it and write something about any subject that shows their feelings. It is the best platform to get text data because most of the people writes here nearly 500 million tweets are sent each day. Sentiment analysis is an opinion mining where sentiments of people can be categorized according to their tweets. The Sentiment Analysis proves its efficiency in analyzing the emotions of the user about a particular subject. There are various algorithms used in this project every algorithm predicts the result but which algorithm is the best suitable that it can predict the best output with same types of data. It can help in categorizing the tweets that how many persons is supporting the subject and how many are not. It can categorize the positive and negative sentence and that can be used for making some important many decisions.
License
This work is licensed under a Creative
Commons
Attribution-ShareAlike 4.0 International License.
Author Information
| # | Name | Institute / Affiliation |
|---|---|---|
| 1 | Deep Ranjan Kumar | RV College of Engineering,Bangalore |
| 2 | Dr Mohan Aradhya | RV College of Engineering,Bangalore |
How to Cite
Use the following formats to cite this article in your research.
APA Style
Kumar, Deep Ranjan & Aradhya, Dr Mohan (2020). Comparative Study of different algorithms in Sentiment Analysis on Twitter. International Journal of Advance Research and Innovative Ideas In Education, 6(3), 665-668.
MLA Style
Kumar, Deep Ranjan, and Dr Mohan Aradhya. "Comparative Study of different algorithms in Sentiment Analysis on Twitter." International Journal of Advance Research and Innovative Ideas In Education, vol. 6, no. 3, 2020, pp. 665-668.
IEEE Style
Deep Ranjan Kumar and Dr Mohan Aradhya, "Comparative Study of different algorithms in Sentiment Analysis on Twitter," International Journal of Advance Research and Innovative Ideas In Education, vol. 6, no. 3, pp. 665-668, 2020.
Vancouver Style
Kumar Deep Ranjan, Aradhya Dr Mohan. Comparative Study of different algorithms in Sentiment Analysis on Twitter. International Journal of Advance Research and Innovative Ideas In Education. 2020;6(3):665-668.
Harvard Style
Kumar, Deep Ranjan & Aradhya, Dr Mohan (2020) 'Comparative Study of different algorithms in Sentiment Analysis on Twitter', International Journal of Advance Research and Innovative Ideas In Education, 6(3), pp. 665-668.
Chicago Style
Kumar, Deep Ranjan and Dr Mohan Aradhya. "Comparative Study of different algorithms in Sentiment Analysis on Twitter." International Journal of Advance Research and Innovative Ideas In Education 6, no. 3 (2020): 665-668.
Turabian Style
Kumar, Deep Ranjan and Dr Mohan Aradhya. "Comparative Study of different algorithms in Sentiment Analysis on Twitter." International Journal of Advance Research and Innovative Ideas In Education 6, no. 3 (2020): 665-668.
Related Research
EduQuest AI: A Gamified Learning Platform for Interactive and Personalized Digital Education
Download PDF
Distributed Real-Time Stream Analytics and Ingestion Engine for High-Velocity Big Data Architectures
Download PDF