ABSTRACT
The current study proposes a topic modeling approach for analyzing press coverage and public perception of distance learning during the COVID-19 pandemic. We evaluate the applicability of a novel approach for neural topic modeling based on transformer-based language models. Our methodology is tested empirically on a large sample of news and discussions in various social and news media platforms to derive valuable insights on press coverage and public perception of COVID-19 impact on the education system in Bulgaria. The study outlines key advantages of using BERTopic in analyzing big data. Our work contributes to the body of literature devoted on value creation through big data and text analytics utilization in the public sector. © 2022 IEEE.
ABSTRACT
The United Nations recently published the "E-govemnient survey 2020" with the main aim of assessing the e- goverament development status of all United Nations member states. The survey outlines 14 leading countries in e- government development (out of 193 member states) some of them claiming to utilize technologies as artificial intelligence (AI). big data and blockchain. Moreover, with the burst of the COVID-19 pandemic the topic on development and implementation of e-government services becomes even hotter. However, along with the research on the process of digitalization of public services, it is important to develop tools measuring how these rapid changes are perceived by the users. Consequently, this paper examines the most recent research devoted on public opinion data mining. On the basis of extensive literanire review, we outline the latest developments and trends in the field of public opinion data mining with special focus on sentiment analysis. Our main goal is to provide a self-contained comprehensive summary that might be used as a basis for design and development of AI systems aimed to mine the public opinion. © 2022 American Institute of Physics Inc.. All rights reserved.
ABSTRACT
Digitalization affects all fields of the modem world including the economic, political, and social aspects of our life. Governments are also involved in this process. Considering the rapid transition towards digital e-services that we evidence since the COVID-19 outbreak, the detection and analysis of public opinion on e-goverament sen-ices becomes even more important. The sentiments and opinions of users on digital public services might be used to foster improvements in the development and implementation of the e-services. In this paper ;.ve engage the advances in NLP so as to examine the possibilities to analyze in an automated manner the opinions and sentiments towards e-goverament services expressed by citizens in various social networks in Bulgaria and this is the main goal of our research. For this purpose, we design an integrated ML-based AI system that aims to support decision makers in e-government and public services provision. The system utilizes a variety of data sources - news websites, web forums and other online social networks. To the best of the authors" knowledge, this is the first study that develops a methodology for mining public opinion in Bulgaria based on a combination of NLP and ML techniques, rather than relying on surveys or in-depth interviews. © 2022 American Institute of Physics Inc.. All rights reserved.
ABSTRACT
COVID-19 has become a global pandemic affecting more than 260 million people and taking more than 5 million lives (WHO data from December 2021). The infection has a unique interaction with the cardiovascular system and is associated with an increased risk of arterial and venous thromboembolic complications. Aim: To evaluate the impact of the COVID-19 pandemic and the concomitant COVID-19 infection on the characteristics of patients with acute myocardial infarction (AMI) and its course. Material and methods: We analyzed all patients admitted for AMI with and without ST-segment elevation for the period November 1, 2020 - February 1, 2021, at National Heart Hospital, and they were further compared according to the presence of COVID-19 infection. The control group included patients with AMI treated between March 13 and May 13, 2019 when no case of COVID-19 had been reported worldwide. The comparative characteristics include risk profile, index event, examinations and treatment performed, and the scores GRACE, CRUSADE, SAPS II, APACHE II and mSOFA.