Applications of Pipelining With ML to Authenticate Emotions in Textual Contents

Applications of Pipelining With ML to Authenticate Emotions in Textual Contents

Yati Varshney, Markandey Sharma, Sonali Jaiswal, Mayank K. Gupta, Rohit Rastogi
Copyright: © 2024 |Pages: 29
DOI: 10.4018/979-8-3693-1082-3.ch014
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

This research chapter aims to provide a smart approach for Human - Machine Interaction development using emotion detection on textual content. These texts can be anything like reviews, tweets, and any form of passage. As the machine is being advanced so that all the performance and commands are given in the text form. This is necessary to analyze the textual content for getting better performance and making the machines smarter. As the customers share their views on social media through the reviews, this mechanism is now spread across all the organization. Nowadays, the number of reviews and tweets are increasing and there is a necessity to analyze the data for further results. In this research, the team analyzes the tweets content in the forms of emotions in which there are multiple forms of the emotions. The machine learning approach is used with tf-idf vectorization for more accuracy. In the presented research, the team performs four machine learning algorithms for analysis; these include Naive Bayes and support vector machine.
Chapter Preview
Top

Topic Organization

This study gives a smart city approach to our country. A country produces a large amount of textual content on social media i.e. reviews. All the content can be classified using this methodology. For the endorsement of the study, the author team did a survey and reviewed four research papers of concerned topics, etc. Survey provides us deep knowledge about the accuracy of the reviews in different companies and how many reviews are helpful for a quick suggestion.

The author team has described the methodology in which they have represented the methods used for the study. This study used the ML based analysis of the textual content. Further, the paper discusses the analysis techniques and how to analyze textual content, what will be the emotions of that data.

To overcome the topics and problems identified in the evaluation, different types of applications and suggestions have been given here. Emotion detection is one of the most important parts in the field of research, according to the recommendation section given in this research paper. The new features of this research is defined in the novelties and at the end the conclusion portion shows the brief detail of the research.

Ethical Committee and Funding

The research have no human related experiments. No violation of the ethics constraints. As the title says there is not any kind of damaging of the nature and humans. This research is not funded.

Role of Authors

Rohit Rastogi acted as team leader and coordinated among all co-authors. He got the topic declared and did a deep study about it and told the co-author about its background and has also helped a lot in emotion detection. He also prepared the structure of the manuscript and ensured the quality of the content along with all co-authors. Ms. Yati did the data analysis. The experimental analysis along with the concluding remarks has been done by Mr. Markandey and Ms. Sonali. All the co-authors have compiled the literature survey along with graphical Representations. Ms. Yati and Markandey contributed to the results and discussions along with concluding remarks.

Top

Introduction

Emotion detection or opinion mining is the method to identify the emotion of the textual content. These textual content can be anything like reviews, comment, message or any phrase. Emotion detecThis textual contententiment analysis but with multiple classes which are the emotions like sadness, joy, happiness, neutral, love, surprise, etc. In this paper the team uses 9 emotions or classes.

Key Terms in this Chapter

Unsupervised Algorithm: The goal of unsupervised algorithm is to find the underlying structure of the dataset, group that data according to similarities, and represent that dataset in a compressed format.

Complete Chapter List

Search this Book:
Reset