Analysis of Romanian Online News Articles Regarding Covid-19 Vaccines Using Nlp Techniques

Understanding the relationship between online media and vaccine-related information is essential for public inoculation strategies. Despite the advent of automated methods for this purpose, there is a gap in terms of applying Natural Language Processing techniques (NLP) to understand information regarding COVID-19 vaccines in Romanian online news. In this sense, this pilot study aims to close the gap by using NLP techniques to analyze information related to vaccines in online news articles. A corpus of 5,670 vaccine-related online news articles published between January and December 2021 was analyzed using sentiment and word cloud analyses to understand the valence and content of COVID-19 vaccine -related information. The results indicate the utility of the proposed method for public and private actors, as well as further required efforts for using NLP techniques to understand and monitor information regarding vaccines present in Romanian online news articles.

ORGANIZATIONAL E-LEARNING IN THE COVID-19 PANDEMIC CONTEXT: A ROMANIAN CASE-STUDY

E-learning concepts gained significant importance in the last decade, tending to be more and more attractive to companies, as skilled employees are the biggest asset of a company. Companies have included e-learning into their business operations. E-learning supports learners with some special capabilities such as interactivity, strong search, immediacy, physical mobility and situating of educational activities, self-organized and self-directed learning, corporate training, personalized learning, and effective technique of delivering lesson and gaining knowledge Because in the last year most companies embraced the “work from home” method, the management needed to take some measures and convert their usual teaching/learning techniques to online trainings. The current paper examines the impact of organizational e-learning on Romanian employees’ productivity, performance, and skills. This study is supported by an innovative online survey from different Romanian public and private organizations and qualitative interviews with some of the participants. The results concluded there is a correlation between e-learning usage and job productivity, performance, and satisfaction. Also, the advantages, the drawbacks of e-learning and the key factors for implementing it successfully were underlined in this paper. © 2021, National Defence University - Carol I Printing House. All rights reserved.

What are the Latest Cybersecurity Trends? A Case Study Grounded in Language Models

The year 2020 marked an important moment when the COVID-19 pandemic promoted Internet as a necessity even more than before, especially for school activities and businesses. This increased usage emphasized the importance of cybersecurity, a frequently overlooked subject by the common users, which in return plays a crucial role in safe Internet browsing. This paper introduces an approach grounded in Natural Language Processing techniques to identify the main trends in security news and empowers the analysis of vulnerable products, active attacks, as well as existing methods of defence against new attacks. Our dataset consists of 2264 news articles published on cybersecurity dedicated websites between January 2017 and May 2021. The RoBERTa language model was used to compute the texts embeddings, followed by dimensionality reduction techniques and topic clustering methods. Articles were grouped into approximately 20 clusters that were thoroughly evaluated in terms of importance and evolution. © 2021 IEEE.

Dialogism Meets Language Models for Evaluating Involvement in CSCL Conversations

The use of technology as a facilitator in learning environments has become increasingly prevalent with the global pandemic caused by COVID-19. As such, computer-supported collaborative learning (CSCL) gains a wider adoption in contrast to traditional learning methods. At the same time, the need for automated tools capable of assessing and stimulating collaboration between participants has become more stringent, as human monitoring of the increasing volume of conversations becomes overwhelming. This paper introduces a method grounded in dialogism for evaluating students’ involvement in chat conversations based on semantic chains computed using language models. These semantic chains reflect emergent voices from dialogism that span and interact throughout the conversation. Our integrated method uses contextual information captured by BERT transformer models to identify links in a chain that connects semantically related concepts from a voice uttered by one or more participants. Two types of visualizations were generated to depict the longitudinal propagation and the transversal inter-animation of voices within the conversation. In addition, a list of handcrafted features derived from the constructed chains and computed for each participant is introduced. Several machine learning algorithms were tested using these features to evaluate the extent to which semantic chains are predictive of student involvement in chat conversations. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

READERBENCH - AUTOMATED FEEDBACK GENERATION FOR ESSAYS IN ROMANIAN

The development of online environments has transformed written communication into one of the most frequently used types of interactions between individuals;this effect has increased even more during the COVID-19 pandemic, which imposed physical distancing restrictions. As writing is a key skill in everyday activities, it is important for people to have strong skills and to be capable to communicate their thoughts and beliefs in a structured form. This paper introduces automated scoring and feedback mechanisms for Romanian, derived from an online collection of freely available essays, and integrated in the ReaderBench platform. Several regression models are evaluated in terms of essay scoring accuracy, out of which Gradient Boosting Regression was selected based on its performance (R-2 = .42, MAE = 1.10 on a 10-point scale). The feedback mechanisms provide suggestions for improving the quality of writings based on several rules, which in turn rely on the textual complexity indices computed by the ReaderBench framework, together with meaningful components generated from a Principal Component Analysis.

GRAPH CONVOLUTIONAL NETWORKS APPLIED TO FAKENEWS: CORONA VIRUS AND 5G CONSPIRACY

The 2020 outbreak of coronavirus pandemic generated a wave of rumours, misinformation, and conspiracy theories;these theories and uninformed speculations gained significant traction through social media platforms. In this paper, we focus on a particular conspiracy theory, related to the unfounded connection between 5G networks and the spread of COVID-19. Several experiments with different types of text classifiers, based on Graph Convolutional Networks enhanced by BERT models, are performed on the MediaEval 2020 5G conspiracy dataset. We show that tweets supporting these theories can be detected with a Matthews Correlation Coefficient score of 0.4975 through state-of-the-art deep learning models. In addition, transfer learning from tasks related to fake news and propaganda improve the performance of our models.

Mouse models and SARS-CoV-2

Since December 2019, a novel coronavirus SARS-CoV-2 has emerged and rapidly spread throughout the world, resulting in a global public health emergency. COVID-19 is causing a major once-in-a century global pandemic. The emergences of coronaviruses have caused a serious global public health problem because their infection in humans caused the severe acute respiratory disease and deaths. Much more serious than SARS-CoV in 2002, the current SARS-CoV-2 infection has been spreading to more than 213 countries, areas or territories and causing more than 31 million cases and 962,518 deaths (update september 2020). Intensive research efforts have focused on increasing our understanding of viral biology of SARS-CoV-2, improving antiviral therapy and vaccination strategies. The lack of vaccine and antivirals has brought an urgent need for an animal model. The animal models are important for both the fundamental research and drug discovery of coronavirus.

Contact Tracing App for Containing Diseases Spread

When dealing with diseases spread, infectious epidemiologists play a vital role. To support them, but also to offer a self-protecting tool to everyone in the context of COVID- 19 pandemic, we propose a cross platform app to track the infected persons, by using their location history. The paper shortly presents the Covid-19 Contacts Tracker App working principle and technologies, as well as issues related to data privacy and security and how we solve them. We claim that the app might be useful in any diseases spread, not only in the current global situation. © 2020 IEEE.