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.

Forecasting COVID-19 Vaccination Rates using Social Media Data

The COVID-19 pandemic has had a profound impact on the global community, and vaccination has been recognized as a crucial intervention. To gain insight into public perceptions of COVID-19 vaccines, survey studies and the analysis of social media platforms have been conducted. However, existing methods lack consideration of individual vaccination intentions or status and the relationship between public perceptions and actual vaccine uptake. To address these limitations, this study proposes a text classification approach to identify tweets indicating a user's intent or status on vaccination. A comparative analysis between the proportions of tweets from different categories and real-world vaccination data reveals notable alignment, suggesting that tweets may serve as a precursor to actual vaccination status. Further, regression analysis and time series forecasting were performed to explore the potential of tweet data, demonstrating the significance of incorporating tweet data in predicting future vaccination status. Finally, clustering was applied to the tweet sets with positive and negative labels to gain insights into underlying focuses of each stance. © 2023 ACM.

IR-ER- A Hybrid Pipeline for Classifying COVID-19 RNA Seq Data

Bioinformatics has numerous approaches for evaluating the similarities between RNA-seq data for disease classification. Processing RNA-sequencing (RNA-seq) data using clustering or classification approach is extremely challenging, although analysis of ribonucleic acid (RNA-Seq) helps understand differentially expressed genes and classify the patient in a risk-free method. In this study, we present a hybrid end-to-end pipeline for analyzing, processing, and classifying the RNA-Seq data with a major focus on the covid-19 data set. The pipeline has been developed in three phases initially the raw data is normalized. Then the normalized data is pushed to a colonization algorithm to remove the noise data. The optimized data set is passed to a Deep Learning (DL) classifier. Further, a comparative analysis is performed with state of art methods discussed in the literature. The results prove that our proposed hybrid pipeline achieved the best accuracy over other methods. Gene set enrichment analysis was also performed to analyze the genes that are informative towards COVID-19 identification. © 2023 ACM.

Performance Analysis of Machine Learning Classification Approaches for Monkey Pox Disease Prediction

After covid-19 pandemic, many countries have the possibility of getting affected by Monkey Pox Virus. Monkey pox has the same symptoms of smallpox, chicken pox, and measles virus. In this work, the computational models are construed to predict the presence or absence of monkey pox virus. Eight different Classification algorithms including Decision Tree (DT), Random Forest Classification (RF), Naïve Bayes (NB), K-Nearest Neighbor algorithms (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Ada Boosting algorithm (AB), Gradient Boosting (GB) algorithm are used for the Classification of Monkey Pox disease. Four evaluation measures are used in this work to compute the accuracy of classification. Four measures F-Score, Accuracy, Precision, and Recall are used to compare the eight different types of classification algorithms. Based on experimental analysis, it was observed that highest accuracy of 71% is achieved by Gradient Boosting algorithm when compared to other algorithms. © 2022 IEEE.

Voting Classification Approach for Covid-19 Prediction with K-mean and PCA

Coronavirus Disease 2019 is occurred as a challenging disease among the scientist worldwide. The disease is developed at an extensive level. Thus, the disease must be detected, reported, isolated, diagnosed and cured at initial phase for mitigating its growth rate. This research paper is conducted on the basisof predicting covid-19 ML algorithms. The methods of predicting this disease consist of diverse stages inwhich data is added as input, pre-processed, attributes are extracted and data is classified. This research work focuses on gathering the authentic dataset which get pre-processed for the classification. In the phase of feature extraction,PCA and k-mean algorithms are applied. The votingclassification method is applied in this work in which GNB, BNB, RF and Support Vector Machine algorithms are integrated. Python is executed to implement the introduced method. Diverse metrics are considered to analyze the outcomes. Using supervised machine learning, we create this model. The branch of ML focuses on implementing intelligent models so that various complicated issues can be tackled. The introduced method offers higher accuracy, precisionand recall in comparison with other classifiers. © 2022 IEEE.

Satellite Data Investigation for Change Estimation During COVID Era by Fusing Pixel and Object-Based Technique

In this investigation, an innovative combination of pixel-based change detection technique and object-based change detection technique is explored with the satellite images of Holy Masjid al-Haram, Saudi Arabia. The gray-level co-occurrence matrix (GLCM) method is used to quantify the texture of the remote sensing data through the texture classification approach on the satellite data in this work. GLCM produces results of the texture quantification in normalized form. Thus, applying a texture classification scheme on the satellite data is impressive to observe. Later maximum likelihood image classification approach is used for classification purposes. The classified information is categorized into four different classes. The kappa coefficient’s value and the overall accuracy for the pre- COVID classified study area are 0.6532 and 76.38%, respectively. During COVID, the classified study area presents the kappa coefficient and the overall accuracy of 0.7631 and 82.18%, respectively. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A Novel Hybrid Classification Approach for Predict Performance Student in E-learning

Predicting educators' learning outcomes at some stage in their educational career has gotten a considerable interest. It supplied essential facts that can aid and recommend universities in making rapid judgments and upgrades that will enhance the success of students. In the tournament of the COVID-19 epidemic, the boom of e has increased, enhancing the quantity of digital studying data. As a result, machine learning (ML)-based algorithms for predicting students’ performance in virtual classes have been developed. Our proposed prediction is a novel hybrid algorithm for predicting the achievements of freshmen in online courses. To enhance prediction results, hybrid gaining knowledge of mix many models. The Voting is a useful technique that is extremely fine when solely one model is present. The researchers concluded that our approach used to be the most successful accuracy performance of 99%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

MeVer team tackling Corona virus and Conspiracies using Ensemble Classification

This paper presents the approach developed by the Media Verification (MeVer) team to tackle the task of Corona Virus and Conspiracies Multimedia Analysis Task at the MediaEval 2021 Challenge. We utilized ensemble learning and propose a two-stage classification approach that aims to overcome the challenge of the imbalanced and relatively small training dataset. We deal with the problem as binary classification in the first stage and in the second stage we predict the multi-labels. We experimented with fine-tuning pre-trained Bidirectional Encoder Representations from Transformers (BERT) and achieved a score of 0.294 in terms of the Matthews Correlation Coefficient (MCC), which is the official evaluation metric of the task. Additionally, leveraging on the proposed two-stage classification approach, we extracted a set of feature representations (BoW, TfIDF, embeddings) and classify them using traditional machine learning algorithms (Support Vector Machines, Logistic Regression) achieving in the best run a score of 0.292 of MCC. Copyright 2021 for this paper by its authors.

Masked Face Detection Using A Two-stage Classification Approach in the COVID-19 Era

Masked face detection is a challenging task in the surveillance applications due to complex backgrounds. In this paper, we propose a two-stage method for masked face detection: pre-detection and verification. Firstly, a masked face detector based on AdaBoost algorithm and histogram of orientation feature is exploited. It may provide sufficient candidate face regions. Secondly, a two-class classifier is trained by broad learning system, which is an incremental learning algorithm with high efficiency in training. It is used to distinguish realistic masked faces from background. Moreover, this paper proposes a masked face dataset that includes multiple masked faces captured from real-life scenes. It can be used for classifier training and evaluation. Experiments conducted on the dataset indicate the effectiveness of the proposed method with Recall 94.69% and Precision 97.72%. © 2021 IEEE.

Hate speech and topic shift in the covid-19 public discourse on social media in Italy

The availability of large annotated corpora from social media and the development of powerful classification approaches have contributed in an unprecedented way to tackle the challenge of monitoring users' opinions and sentiments in online social platforms across time but also arose the challenge of temporal robustness of such detection and monitoring systems. We used as case study a dataset of tweets in Italian related to the COVID-19 induced lockdown in Italy to measure how quickly the most debated topic online shifted in time. We concluded that it is a promising approach but dedicated corpora and fine tuning of algorithms are crucial for more insightful results. © 2021 for this paper by its author. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).