Dangi Dharmendra, Dixit Dheeraj K, Bhagat Amit
Department of Mathematics, Bioinformatics and Computer Applications, Maulana Azad National Institute of Technology, Bhopal, India.
Multimed Tools Appl. 2022;81(29):42261-42283. doi: 10.1007/s11042-022-13492-w. Epub 2022 Jul 25.
Pandemics are a severe threat to lives in the universe and our universe encounters several pandemics till now. COVID-19 is one of them, which is a viral infectious disease that increased morbidity and mortality worldwide. This has a negative impact on countries' economies, as well as social and political concerns throughout the world. The growths of social media have witnessed much pandemic-related news and are shared by many groups of people. This social media news was also helpful to analyze the effects of the pandemic clearly. Twitter is one of the social media networks where people shared COVID-19 related news in a wider range. Meanwhile, several approaches have been proposed to analyze the COVID-19 related sentimental analysis. To enhance the accuracy of sentimental analysis, we have proposed a novel approach known as Sentimental Analysis of Twitter social media Data (SATD). Our proposed method is based on five different machine learning models such as Logistic Regression, Random Forest Classifier, Multinomial NB Classifier, Support Vector Machine, and Decision Tree Classifier. These five classifiers possess various advantages and hence the proposed approach effectively classifies the tweets from the Twint. Experimental analyses are made and these classifier models are used to calculate different values such as precision, recall, f1-score, and support. Moreover, the results are also represented as a confusion matrix, accuracy, precision, and receiver operating characteristic (ROC) graphs. From the experimental and discussion section, it is obtained that the accuracy of our proposed classifier model is high.
大流行对宇宙中的生命构成严重威胁，到目前为止，我们的宇宙已经遭遇了几次大流行。新冠疫情就是其中之一，它是一种病毒性传染病，在全球范围内增加了发病率和死亡率。这对各国经济以及全球的社会和政治问题都产生了负面影响。社交媒体的发展见证了许多与大流行相关的新闻，并被许多人群分享。这些社交媒体新闻也有助于清晰地分析大流行的影响。推特是人们广泛分享新冠疫情相关新闻的社交媒体网络之一。与此同时，已经提出了几种方法来分析与新冠疫情相关的情感分析。为了提高情感分析的准确性，我们提出了一种新颖的方法，称为推特社交媒体数据情感分析（SATD）。我们提出的方法基于五种不同的机器学习模型，如逻辑回归、随机森林分类器、多项式朴素贝叶斯分类器、支持向量机和决策树分类器。这五个分类器具有各自的优势，因此所提出的方法有效地对来自Twint的推文进行分类。进行了实验分析，并使用这些分类器模型来计算不同的值，如精度、召回率、F1分数和支持度。此外，结果还以混淆矩阵、准确率、精度和接收器操作特征（ROC）图的形式呈现。从实验和讨论部分可以得出，我们提出的分类器模型的准确率很高。
