Opinions cum sentiments of the textual content through ML methods: a smart city-based approach in 21st century using NLP
by Rohit Rastogi; Yati Varshney; Sonali Jaiswal; Markandey Sharma
International Journal of Creative Computing (IJCRC), Vol. 2, No. 1, 2023

Abstract: The ambition of this research is to advance a functional classifier for automatic and error-free sentiment classification of an unknown tweet stream. In the past decades, new shape of communication, such as text messaging and microblogging have come up and become universal. Beside there is no range of information to be transmit by text and tweets, often these message are used to give opinions and sentiment that people have around what is going around on the world. The researcher team also worked on the following task. The task was to give a message, so as to categorise whether the message is of positive, negative or neutral sentiment. The corpus-base method was used to find semantic orientation of dictionary-based method and adjectives to find the semantic orientation of adverb and verbs. Algorithms used in this research are Naive Bayes classifier, decision tree, AdaBoost classifier, random forest, support vector machine, KNN classifier, 7XGBOOST and logistic regression. The work in this paper gives a novel approach for sentiment analysis on data. The initial result shows it is a motivating technique.

Online publication date: Wed, 20-Sep-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Creative Computing (IJCRC):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com