A Classification Approach to Detect Public Sentiments towards COVID-19 Vaccines

In this paper, team University of Botswana Computer Science (UBCS) investigate the opinions of Twitter users towards vaccine uptake. In particular, we build three different text classifiers to detect people's opinions and classify them as provax-for opinions that are for vaccination, antivax for opinions against vaccination and neutral-for opinions that are neither for or against vaccination. Two different datasets obtained from Twitter, 1 by Cotfas and the other by Fire2022 Organizing team were merged to and used for this study. The dataset contained 4392 tweets. Our first classifier was based on the basic BERT model and the other 2 were machine learning models, Random Forest and Multinomial Naive Bayes models. Naive Bayes classifier outperformed other classifiers with a macro-F1 score of 0.319. © 2022 Copyright for this paper by its authors.

Towards Detection of Cyberbullying in Hinglish Code Mixed Data

Covid-19 eruption and lockdown situation have increased the usages of online platforms which have impacted the users. Cyberbullying is one of the negative outcomes of using social media platforms which leads to mental and physical distress. This study proposes a machine learning-based approach for the detection of cyberbullying in Hinglish text. We use the Hinglish Code-Mixed Corpus, which consists of over 6,000 tweets, for our experiments. We use various machine learning algorithms, including Logistic regression (LR), Multinomial Naive Bayes (MNB), Support vector machine (SVM), Random Forest (RF), to train our models. We evaluate the performance of the models using standard evaluation metrics such as precision, recall, and F1-score. Our experiments show that the LR with Term Frequency-Inverse Document Frequency (TFIDF) outperforms the other models, achieving 92% accuracy. Our study demonstrates that machine learning models can be effective for cyberbullying detection in Hinglish text, and the proposed approach can help identify and prevent cyberbullying on social media platforms. © 2023 Bharati Vidyapeeth, New Delhi.

Changes in public travel willingness in the post-COVID-19 era: Evidence from social network data

Amid the impact of COVID-19, the public's willingness to travel has changed, which has had a fundamental impact on the ridership of urban public transport. Usually, travel willingness is mainly analyzed by questionnaire survey, but it needs to reflect the accurate psychological perception of the public entirely. Based on Weibo text data, this paper used natural language processing technology to quantify the public's willingness to travel in the post-COVID-19 era. First, web crawler technology was used to collect microblog text data, which will discuss COVID-19 and travel at the same time. Then, based on the Naive Bayes classification algorithm, travel sentiment analysis was carried out on the data, and the relationship between public travel willingness and urban public transport ridership was analyzed by Spearman correlation analysis. Finally, the LDA topic model was used to conduct content topic research on microblog text data during and after COVID-19. The results showed that the mean values of compelling travel emotion were-0.8197 and-0.0640 during and after COVID-19, respectively. The willingness of the public to travel directly affects the ridership of urban public transport. Compared with the COVID-19 period, the public's fear of travel infection in the post-COVID-19 era has significantly improved, but it still exists. The public pays more attention to the level of COVID-19 prevention and control and the length of travel time on public transport.

Integration of Adaptive Collaborative Learning Process in a Hybrid Learning Environment

Technology integration has been crucial in the practice of the learning process. The use of technology aims to find effective solutions to traditional learning problems. Despite the enormous efforts adopted, using e-learning systems was optional in many education systems. However, the COVID-19 health crisis has shown the importance of the transition to e-learning to ensure pedagogical continuity. According to several studies that have measured the impact of COVID-19 on education systems and the adopted solutions, blended learning represents an effective solution for combining the advantages of face-to-face and distance learning. But the implementation strategies regarding this mode of learning are still limited. For this purpose, we propose a hybrid learning model based on collaborative work through an intelligent assignment of learner roles. This approach aims to support adaptive learning via a hybrid learning environment. The proposed solution is based mainly on collaborative work as an active learning method, using the Naïve Bayes algorithm and Belbin theory. The usefulness of collaborative work is to keep the learning rhythm between face-to-face and distance learning and to encourage learners' engagement and motivation through this mode of learning. According to Belbin's theory, the results of this work propose an adequate role for each learner. This intelligent assignment leads the learner to live the learning situation and not undergo it. © IJASEIT is licensed under a Creative Commons Attribution-Share Alike 4.0 International License.

COMPARISON OF THE ACCURACY OF THE LEXICON-BASED AND NAIVE BAYES CLASSIFIER METHODS TO PUBLIC OPINIONS ABOUT REMOVING MASKS ON SOCIAL MEDIA TWITTER

At the beginning of 2020 the world was shocked by the COVID-19 pandemic which paralyzed all aspects of activity for some time. However, over time and with the discovery of a vaccine, the cases caused by COVID-19 began to subside. In 2022, the Indonesian government make a policy that people are allowed to take off their masks when active but are encouraged to maintain health protocols. However, the approach reaped the pros and cons of the Indonesian people. One challenge is to build technology to detect and summarize an overall those pros and cons. So that, we look at Twitter and build models for classifying ‘tweets' into positive, negative and neutral sentiment using top two approaches for sentiment analysis, the lexicon-based method and the naive Bayes classifier. This study aimed to analyze public opinion about removing masks through Twitter by comparing the lexicon-based method and the naive Bayes classifier method to find out how the community responded to taking off masks. A total of 639 tweets with the keyword "Lepas Masker" was analyzed include data crawling, text preprocessing, feature extractions and the classification process. The comparison of the results obtained shows the accuracy of 82% for the lexicon-based method and 70% for the naive Bayes classifier method. To the results, the accuracy value of the lexicon-based method is higher than the naive Bayes classifier method. © 2023 Little Lion Scientific. All rights reserved.

A Machine Learning-driven IoT Architecture for Predicting the Growth and Trend of Covid-19 Epidemic Outbreaks to Identify High-risk Locations

Covid-19 has had a destructive influence on global economics, social life, education, and technologies. The rise of the Covid-19 pandemic has increased the use of digital tools and technologies for epidemic control. This research uses machine learning (ML) models to identify populated areas and predict the disease's risk and impact. The proposed system requires only details about mask utilization, temperature, and distance between individuals, which helps protect the individual's privacy. The gathered data is transferred to an ML engine in the cloud to determine the risk probability of public areas concerning Covid-19. Extracted data are input for multiple ML techniques such as Random Forest (RF), Decision tree (DT), Naive Bayes classifier(NBC), Neural network(NN), and Support vector machine (SVM). Expectation maximization (EM), K-means, Density, Filtered, and Farthest first (FF) clustering algorithms are applied for clustering. Compared to other algorithms, the K-means produces better superior accuracy. The regression technique is utilized for prediction. The outcomes of several methods are compared, and the most suitable ML algorithms utilized in this study are used to identify high-risk locations. In comparison to other identical architectures, the suggested architecture retains excellent accuracies. It is observed that the time taken to build the model using locally weighted learning(LWL) was 0.02 seconds, and the NN took more time to build, which is 0.90 seconds. To test the model, an LWL algorithm took more time which is 1.73 seconds, and the NN took less time to test, which is 0.02 seconds. The NBC has a 99.38 percent accuracy, the RF classifier has a 97.33 percent accuracy, and the DT has a 94.51 percent accuracy for the same data set. These algorithms have significant possibilities for predicting the likelihood of crowd risks of Covid-19 in a public space. This approach generates automatic notifications to concerned government authorities in any aberrant detection. This study is likely to aid researchers in modeling healthcare systems and spur additional research into innovative technology. © 2023 IEEE.

Analysis of Student Study of Virtual Learning Using Machine Learning Techniques

Since COVID-19 was released, online education has taken center stage. Educational performance analysis is a central topic in virtual classrooms and across the spectrum of academic institutions. This research analyzed students' studies in virtual learning using many machine-learning classifiers, which include LogitBoost, Logistic Regression, J48, OneR, Multilayer Perceptron, and Naive Bayes, to find the ideal one that produces the best outcomes. This research evaluates algorithms based on recall, precision, and f-measure to determine their efficacy. Accordingly, the authors try to perform a comparative analysis of the algorithms in this research by employing two distinct test models: the use of training sets and the 10 cross-fold models. The research results demonstrate that the training set model outperforms the 10 cross-fold model. The findings demonstrate that the multilayer perceptron classifier utilizing the use training set model performs much better in terms of predicting student study in virtual learning.

Sentiment Analysis and Topic Classification of Twitter-based Data Set on the Face-to-face Classes Resumption in the Philippines during the COVID-19 Pandemic

Due to the Corona Virus Disease 2019 (COVID-19) pandemic, there was a need for shift in pedagogy of education. Several delivery modes for educational materials and activities had to be implemented to adapt in the situation brought about by the pandemic. In the Philippines, there has been a call to fully transition to face-to-face classes expressed on social media. In this study, a data set was built consisting of tweets (Twitter data) regarding the resumption of face-to-face classes in the Philippines. This data set was subjected to training and testing to classify them in terms of topic and sentiment using Recurrent Neural Network Long Short-Term Memory (LSTM) and Multinomial Naïve Bayes. The LSTM sentiment classifier resulted to 78.33% accuracy and LSTM topic classifier produced 61.34% accuracy. The Multinomial Naïve Bayes classifier obtained 77.22% accuracy for classifying sentiment while 58.33% accuracy for topic classification. © 2022 IEEE.

A Prediction Model for Screening Covid-19 Patients

This study aims to compare the performance of data classifying for COVID-19 patients. In this study, the patients' data acquired from the department of disease control (1,608,923 patients) are collected. They are patients records from January 2020 to October 2021. The study focus on three main data classification techniques: Random forest;Neural Network;and Naïve Bayes. The authors study the comparative performance of the techniques. We apply the split test method to evaluate the performance of data prediction. The data are divided into two parts: training data. The results show that Random Forest has an accuracy of 93.51%. Neural network has an accuracy of 93.02%. Naive Bayes has an accuracy of 27.54%. This presents the Random Forest with the highest accuracy Figure for screening of COVID-19 patients © 2022 IEEE.

An AdaBoost Method with K′K-Means Bayes Classifier for Imbalanced Data

This article proposes a new AdaBoost method with k′k-means Bayes classifier for imbalanced data. It reduces the imbalance degree of training data through the k′k-means Bayes method and then deals with the imbalanced classification problem using multiple iterations with weight control, achieving a good effect without losing any raw data information or needing to generate more relevant data manually. The effectiveness of the proposed method is verified by comparing it with other traditional methods based on numerical experiments. In the NSL-KDD data experiment, the F-score values of each minority class are also greater than the other methods.

Benign and Malignant Skin Lesion Detection from Melanoma Skin Cancer Images

Skin cancer is the most dangerous and lethal cancer that affects millions of people each year. The accurate identification of skin cancers can not be accomplished without expert dermatologists. However, specific research studies of WHO in Canada, US and Australia, show that in the year 1960s to 1980s, the cases of skin cancer has noted more than two times increased in comparison with the previous years. The identification of skin cancer in its early stage is an expensive and difficult task because it doesn't cause too much bad in the initial phase. Whereas, the growth of skin cancer requires biopsy and many other treatments each time which is quite costly as per the statistics of India. This challenge makes it a necessary step to identify the existence of skin cancer in the early stages to increase immortality. With the evolution and progression in technology, there are various methods which have participated in and solved medical issues including covid19, pneumonia and many others. Similarly, machine learning(ML) and deep learning(DL) models are applicable to diagnosing skin cancer in its early stages. In this work, the support vector machine (SVM), naive bayes (NB), K-nearest neighbour (KNN) and neural networks(NN) have been used for classifying benign and malignant lesions. Furthermore, for the feature extraction from the dataset, a pre-trained SqueezeNet model has been used. The classification results of KNN, SVM, NB and NN have been shown in the accuracy, recall, F1-Measure, precision, AUC and ROC. The comparison of the models has resulted that the NN model outperforms all other models when applied with the SqueezeNet feature extractor with the highest accuracy, F1-Measure, recall, precision and AUC as 88.2%, 0.882, 0.882, 0.882 and 0.957, respectively. Lastly, the performance metrics analogies results of each model have been illustrated for the classification of benign and malignant lesions. © 2023 IEEE.

Evaluation of AI Techniques for Detecting Deceptive Reviews in Cyberspace: A Study of Pre- and Post-COVID-19 Trends

With cyberspace's continuous evolution, online reviews play a crucial role in determining business success in various sectors, ranging from restaurants and hotels to e-commerce applications. Typically, a favorable review for a specific product draws in more consumers and results in a significant boost in sales. Unfortunately, a few businesses are using deceptive methods to improve their online reputation by using fake reviews of competitors. As a result, detecting fake reviews has become a difficult and ever-changing research field. Verbal characteristics extracted from review text, as well as nonverbal features such as the reviewer's engagement metrics, the IP address of the device, and so on, play an important role in detecting fake reviews. This article examines and compares various machine learning techniques for detecting deceptive reviews on various online platforms such as e-commerce websites such as Amazon and online review websites such as Yelp, among others. © 2023 IEEE.

Pandemic Outbreak Time: Evaluation of Public Tweet Opinion by Machine Learning

In this work, a Twitter data-set was utilized to do sentiment analysis of people's thoughts on the corona-virus (COVID-19) period, which is a major concern throughout the world these days, impacting a number of nations. To better understand people's feelings about the epidemic, machine learning approaches (mla) and sentiment methodology such as Bert Model (BMO), Naive_Bayes_Bernoulli (nBB), Multi Nominal Naive_Bayes (mnNB), Support_ Vector_Machine (svM), Logistic_Regression (IR), Gradient_Boosting_ Classifier (gbR), Decision Tree Classifiers (dtC), K N eighbors(knN) and Random Forest Classifier (rfC) have been presented in this work. Also, we have classified that which Classifiers provides highest accuracy. Additionally, in this paper, we also analysis from the data set, the most that has been tweeted (hashtag), positive, negative as well as neutral with data visualization in the Covid-19 epidemic time. © 2022 IEEE.

Social Media Sentiment Analysis on Third Booster Dosage for COVID-19 Vaccination: A Holistic Machine Learning Approach

Over a period of more than two years the public health has been experiencing legitimate threat due to COVID-19 virus infection. This article represents a holistic machine learning approach to get an insight of social media sentiment analysis on third booster dosage for COVID-19 vaccination across the globe. Here in this work, researchers have considered Twitter responses of people to perform the sentiment analysis. Large number of tweets on social media require multiple terabyte sized database. The machine learned algorithm-based sentiment analysis can actually be performed by retrieving millions of twitter responses from users on daily basis. Comments regarding any news or any trending product launch may be ascertained well in twitter information. Our aim is to analyze the user tweet responses on third booster dosage for COVID-19 vaccination. In this sentiment analysis, the user sentiment responses are firstly categorized into positive sentiment, negative sentiment, and neutral sentiment. A performance study is performed to quickly locate the application and based on their sentiment score the application can distinguish the positive sentiment, negative sentiment and neutral sentiment-based tweet responses once clustered with various dictionaries and establish a powerful support on the prediction. This paper surveys the polarity activity exploitation using various machine learning algorithms viz. Naïve Bayes (NB), K- Nearest Neighbors (KNN), Recurrent Neural Networks (RNN), and Valence Aware wordbook and sEntiment thinker (VADER) on the third booster dosage for COVID-19 vaccination. The VADER sentiment analysis predicts 97% accuracy, 92% precision, and 95% recall compared to other existing machine learning models. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Name Entity Recognition on Covid-19 Dataset using Machine Learning algorithms

The COVID-19 pandemic has been accompanied by such an explosive increase in media coverage and scientific publications that researchers find it difficult to keep up. So we are working on COVID-19 dataset on Omicron variant to recognise the name entity from a given text. We collect the COVID related data from newspaper or from tweets. This article covered the name entity like COVID variant name, organization name and location name, vaccine name. It include tokenisation, POS tagging, Chunking, levelling, editing and for run the program. It will help us to recognise the name entity like where the COVID spread (location) most, which variant spread most (variant name), which vaccine has been given (vaccine name) from huge dataset. In this work, we have identified the names. If we assume unemployment, economic downfall, death, recovery, depression, as a topic we can identify the topic names also, and in which phase it occurred. © 2022 IEEE.

Investigating the performance of machine learning algorithms in predicting the survival of COVID-19 patients: A cross section study of Iran.

Background and Aims: Like early diagnosis, predicting the survival of patients with Coronavirus Disease 2019 (COVID-19) is of great importance. Survival prediction models help doctors be more cautious to treat the patients who are at high risk of dying because of medical conditions. This study aims to predict the survival of hospitalized patients with COVID-19 by comparing the accuracy of machine learning (ML) models. Methods: It is a cross-sectional study which was performed in 2022 in Fasa city in Iran country. The research data set was extracted from the period February 18, 2020 to February 10, 2021, and contains 2442 hospitalized patients' records with 84 features. A comparison was made between the efficiency of five ML algorithms to predict survival, includes Naive Bayes (NB), K-nearest neighbors (KNN), random forest (RF), decision tree (DT), and multilayer perceptron (MLP). Modeling steps were done with Python language in the Anaconda Navigator 3 environment. Results: Our findings show that NB algorithm had better performance than others with accuracy, precision, recall, F-score, and area under receiver operating characteristic curve of 97%, 96%, 96%, 96%, and 97%, respectively. Based on the analysis of factors affecting survival, heart disease, pulmonary diseases and blood related disease were the most important disease related to death. Conclusion: The development of software systems based on NB will be effective to predict the survival of COVID-19 patients.

Classification of Covid-19 Vaccines tweets using Naïve Bayes Classification

Recently COVID-19 has become the most discussed topic in different social media platforms like Twitter, Facebook, Instagram etc. As time moves on, lot of messages and videos are posted in social media. As expected, most of the public followed these messages and becomes panic because of lack of information, misinformation about COVID-19 and its impact. This research study proposes a Twitter sentiment analysisbased on the most popular vaccines Covaxin, Covishield, and Pfizer. Most of the people expressed their feelings about vaccines in the twitter. Twitter API authentication is used here to extract the tweets. These extracted tweets are difficult to analyze, hence pre-processing has been done i.e., unstructured data is converted into structured format. After completion of preprocessing, the data is further classified by using Naïve Bayes algorithm. This algorithm performs data classification and divides it into three major classes as positive, negative, and neutral. The result shows that the covaxin yields 48.36% positive, 35.6% negative, and 16.04% neutral, Covishield yields 44.25% positive, 39.67% negative, and 16.08% neutral, Pfizer yields 42.95% positive, 39.45% negative, and 17.6% neutral sentiment. © 2022 IEEE.

A Novel Machine Learning Classification Model to Analyze the COVID-19 Pandemic's Impact on Academics: Sentiment Analysis Approach

The COVID-19 Pandemic is considered as the worst situation for human beings;it affected people's lives worldwide. Due to this pandemic, the respective government authority announced the lockdown to break the coronavirus chain. The lockdown impacted people's mental health, leading to many psychological issues as well as hampered students' academics. In this chapter we have studied the impacts on students' academics due to lockdown effect. The data has been collected via a google form questionnaire circulated to various educational institutes. Further, we have developed a novel machine learning classifier model called Naïve Bayes-Support Vector Machine for analyzing the data, which utilizes the properties of both classifiers by using a deep learning framework. We have used natural language processing (TextBlob, Stanza and Vader) libraries to label the dataset and applied in the proposed NBSVM method and other machine learning models and classified the sentiments into two categories (Positive vs Negative). We also applied the natural language processing libraries used a topic-modelling technique called Latent Dirichlet Allocation to know the essential topics words of both classes from students' feedback data. The study revealed 83% and 86% accuracy for unigram and bigram, respectively, whereas the precision was 79% and recall 81%. According to NLP libraries' result, approximately 71% of the feedback's sentiment is negative, and only 16% of feedbacks are positive. The proposed model shown that (Naïve Bayes-Support Vector Machine) outperforms the other variants of the Naïve Bayes and support vector machine. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A New Hybrid Artificial Intelligence Model for Diseases Identification

Artificial intelligence is increasingly applied in many fields, specially in medicine to assist patients and physicians. Growing datasets provide a sound basis to adapt machine learning methods to identify and detect some diseases. These later, are often very similar which make difficult their identification by chest X-ray images. In this paper, we introduce a diagnostic AI model that allow to separate, diagnose and classify three various diseases: tuberculosis, covid19 and Pneumonia. The proposed model is based on a combination of Deep Learning using the deep SqueezeNet model and Machine Learning: SVM, KNN, Logistic Regression, decision tree and Naive Bayes. The model is applied to a chest X-ray dataset containing images for each type of disease. To train and test our model, we split the image dataset into two training and test subsets in order to differentiate between different disease types. The accuracy show clearly that our model provides better results of diagnosis and identification. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

COVID-19 Detection in the Images of Chest CT Scan Using K-NN in Comparison with NB Classifier to Improve the Accuracy

This chapter is about the improvisation in the accuracy in COVID-19 detection using chest CT-scan images through K-Nearest Neighbour (K-NN) compared with Naive-Bayes (NB) classifier. The sample size considered for this detection is 20, for group 1 and 2, where G-power is 0.8. The value of alpha and beta was 0.05 and 0.2 along with a confidence interval at 95%. The K-NN classifier has achieved 95.297% of higher accuracy rate when compared with Naive Bayes classifier 92.087%. The results obtained were considered to be error-free since it was having the significance value of 0.036 (p < 0.05). Therefore, in this work K-Nearest Neighbor has performed significantly better than Naive Bayes algorithm in detection of COVID-19. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.