Ensemble Learning Approach for Predicting Job Satisfaction on Freelancing Jobs in Sri Lanka

Due to the recent social and economic problems that have occurred locally and globally, Freelance work has gained more attention recently. Specially, working from home or other appropriate workspaces has become more popular during the Covid-19 pandemic situation. Freelancing is a profession worker working for themselves who can perform contract work or tasks either full-or part-time in a range of job fields. to get more accurate Because of the infrastructure facilities like internet, and the situations like pandemic, it is now possible to earn money online. Online freelancing assigns straightforward jobs to workers via online platforms with greater cost effectiveness. The main objective of this study is to build a model through Machine Learning (ML) to predict job satisfaction in freelancing jobs. Primary data used in this research is gathered with help of current freelancers results. After the pre-processing is completed, individual algorithms Naïve Bayes, Support Vector Machine (SVM), Decision Tree (J48), Random Forest, and Multilayer Perception (MLP) separate algorithms and Ensemble Learning approach used as a combination of the above five algorithms. Among them, the best accuracy, precision, recall, and f-measure values as well as lower error rates were obtained through the Ensemble Learning algorithm. The evaluation result proved the effectiveness of our proposed approach. © 2022 IEEE.

An Ensemble Learning Approach for COVID-19 Fact Verification

The rapid development of social media platforms has resulted in a fast-paced spread of misinformation, which is especially common in the COVID-19 pandemic. In the global pandemic, the amount of COVID-19 related fake news generated online becomes enormous, which negatively results in public tension. Moreover, rumours are spread across platforms from different countries in such a global pandemic. Thus, automated fact-checking, which refers to automatically verifying the correctness of a claim, is of great importance. In this paper, we propose and examine ensemble learning approaches that exploit the power of multiple large-scale pre-trained language models. We conduct extensive experiments on traditional approaches, learning-based approaches, and our proposed ensemble methods. We successfully advance state-of-the-art performance by a significant margin. Further, we show that our ensemble method is especially suited to tasks with scarce training data, making it more suitable for many real-world applications. © 2022 IEEE.

VaderLogRest Algorithm: An Ensemble Learning Approach for Sentiment Analysis on Vaccination Tweets

Analyzing the emotions about the vaccines and vaccination will help to successfully carry forward the vaccination trials and government policies towards epidemic control. The tweets featured information on the most common immunizations has recently been available all around the world. The method of natural language processing is the successful tool to investigate the reactions of the people to various immunizations. This paper proposes a ensemble learning model making use of the VADER lexicon, logistic regression, and random forest algorithm for sentiment analysis to understand and interpret the people's sentiments through the tweets. We utilize a collection of tweets in April to May 2021 to extract inferences about public views on vaccinations as they become more widely available during the COVID-19 pandemic. The classification output of the VADER algorithm is used as one more feature that helps to achieve better accuracy using the random forest algorithm. One more feature is added with the available features using logistic regression. Hence, the classification outputs of VADER and logistic regression improve the classification accuracy to 88% for positive-negative outputs and 84% for positive, neutral, and negative outputs. © 2022 IEEE.

Learning complementary representations via attention-based ensemble learning for cough-based COVID-19 recognition

Coughs sounds have shown promising as-potential marker for distinguishing COVID individuals from non-COVID ones. In this paper, we propose an attention-based ensemble learning approach to learn complementary representations from cough samples. Unlike most traditional schemes such as mere maxing or averaging, the proposed approach fairly considers the contribution of the representation generated by each single model. The attention mechanism is further investigated at the feature level and the decision level. Evaluated on the Track-1 test set of the DiCOVA challenge 2021, the experimental results demonstrate that the proposed feature-level attention-based ensemble learning achieves the best performance (Area Under Curve, AUC: 77.96%), resulting in an 8.05% improvement over the challenge baseline. ©