Comparison of Parameters
of Sentimental Analysis Using Different
Classifiers
Akash Yadav and Ravinder Ahuja
1 Introduction
Nowadays, we see the usage of social media is increasing exponentially, and by this,
various sectors are targeting social media platform as their launch pad for example—
usage of social media in influence the elections self-promotions, etc., so there is need
to analyze the opinion as it draws responses to various responses available on social
media. Twitter is one place where people view their views very strongly on different
issues. For examining user thoughts, sentimental analysis has become a significant
source for the purpose of solving hidden pattern in a large number of tweets with the
help of machine learning algorithms. We prepared our work with ten algorithms to
sort outperformance of classifiers. We used feature extraction and machine learning
algorithm in two different entities. Our main contribution is to find out the best
classification algorithm to be applied to get the maximum potential of sentimental
analysis by comparing four significant factors of performance of each classification
algorithm which is described as F1-score, precision, accuracy, and recall.
2 Related Work
The sentiment140 dataset we used in our work was generated using the automated
labeling method [1]. Baccianella et al. [1] they used automation to take the lead
A. Yadav (B ) · R. Ahuja
School of Computing Science and Engineering, Galgotias University, Greater Noida, Uttar
Pradesh, India
e-mail: akashyadav1197@gmail.com
R. Ahuja
e-mail: ahujaravinder022@gmail.com
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021
V. K. Gunjan et al. (eds.), Cybernetics, Cognition and Machine
Learning Applications, Algorithms for Intelligent Systems,
https://doi.org/10.1007/978-981-33-6691-6_44
403