RESUMEN
The Coronavirus pandemic has taken the world hostage. All aspects of society have been affected, including the education system with the closure of universities and the adoption of abrupt measures to continue offering university programs virtually. Unexpectedly, the difficult situation has continued until at least December 2021. This paper studies the evolution of the perceived impact of the pandemic on students over four semesters, from Winter 2020 to Fall 2021. A survey conducted at the end of each semester captured the evolution of the impact felt by students. Using Text Mining and Sentiment Analysis, per semester, per gender and per age category, the progression of certain sentiments was identified. The study reveals that the professor's attitude and support was a key element at the beginning of the pandemic and for many, it has been a good learning experience overall. The loss of direct/in person communication has been strongly felt and it got worse as time progresses. The level of negative comments seems to decrease over time for Female students, while for Male students, it tends to increase. Students from different age groups also reacted differently. Students in the most prevalent age group from age 25 to 30 show at first a decline in the proportion of negative comments followed by an increase, while older students from the 30 to 35 age group have a steady decrease of negativity. © 2023 by the authors.
RESUMEN
Objective Based on text mining technology and biomedical database, data mining and analysis of coronavirus disease 2019 (COVID-19) were carried out, and COVID-19 and its main symptoms related to fever, cough and respiratory disorders were explored. Methods The common targets of COVID-19 and its main symptoms cough, fever and respiratory disorder were obtained by GenCLiP 3 website, Gene ontology in metascape database (GO) and pathway enrichment analysis, then STRING database and Cytoscape software were used to construct the protein interaction network of common targets, the core genes were screened and obtained. DGIdb database and Symmap database were used to predict the therapeutic drugs of traditional Chinese and Western medicine for the core genes. Results A total of 28 gene targets of COVID-19 and its main symptoms were obtained, including 16 core genes such as IL2, IL1B and CCL2. Through the screening of DGIdb database, 28 chemicals interacting with 16 key targets were obtained, including thalidomide, leflunomide and cyclosporine et al. And 70 kinds of Chinese meteria medica including Polygonum cuspidatum, Astragalus membranaceus and aloe. Conclusion The pathological mechanism of COVID-19 and its main symptoms may be related to 28 common genes such as CD4, KNG1 and VEGFA, which may participate in the pathological process of COVID-19 by mediating TNF, IL-17 and other signal pathways. Potentially effective drugs may play a role in the treatment of COVID-19 through action related target pathway.Copyright © 2022 Tianjin Press of Chinese Herbal Medicines. All Rights Reserved.
RESUMEN
The spread of health misinformation has the potential to cause serious harm to public health, from leading to vaccine hesitancy to adoption of unproven disease treatments. In addition, it could have other effects on society such as an increase in hate speech towards ethnic groups or medical experts. To counteract the sheer amount of misinformation, there is a need to use automatic detection methods. In this paper we conduct a systematic review of the computer science literature exploring text mining techniques and machine learning methods to detect health misinformation. To organize the reviewed papers, we propose a taxonomy, examine publicly available datasets, and conduct a content-based analysis to investigate analogies and differences among Covid-19 datasets and datasets related to other health domains. Finally, we describe open challenges and conclude with future directions.
RESUMEN
An innovative ADE-TFT interpretable tourism demand forecasting model was proposed to address the issue of the insufficient interpretability of existing tourism demand forecasting. This model effectively optimizes the parameters of the Temporal Fusion Transformer (TFT) using an adaptive differential evolution algorithm (ADE). TFT is a brand-new attention-based deep learning model that excels in prediction research by fusing high-performance prediction with time-dynamic interpretable analysis. The TFT model can produce explicable predictions of tourism demand, including attention analysis of time steps and the ranking of input factors' relevance. While doing so, this study adds something unique to the literature on tourism by using historical tourism volume, monthly new confirmed cases of travel destinations, and big data from travel forums and search engines to increase the precision of forecasting tourist volume during the COVID-19 pandemic. The mood of travelers and the many subjects they spoke about throughout off-season and peak travel periods were examined using a convolutional neural network model. In addition, a novel technique for choosing keywords from Google Trends was suggested. In other words, the Latent Dirichlet Allocation topic model was used to categorize the major travel-related subjects of forum postings, after which the most relevant search terms for each topic were determined. According to the findings, it is possible to estimate tourism demand during the COVID-19 pandemic by combining quantitative and emotion-based characteristics.
RESUMEN
Introduction: The COVID-19 pandemic has triggered a massive acceleration in the use of virtual and video-visits. As more patients and providers engage in video-visits over varied digital platforms, it is important to understand how patients assess their providers and the video-visit experiences. We also need to examine the relative importance of the factors that patients use in their assessment of video-visits in order to improve the overall healthcare experience and delivery. Methods: A data set of 5149 reviews of patients completing a video-visit was assembled through web scraping. Sentiment analysis was performed on the reviews and topic modeling was used to extract latent topics embedded in the reviews and their relative importance. Results: Most patient reviews (89.53%) reported a positive sentiment towards their providers in video-visits. Seven distinct topics underlying the reviews were identified: bedside manners, professional expertise, virtual experience, appointment scheduling and follow-up process, wait times, costs, and communication. Communication, bedside manners and professional expertise were the top factors patients alluded to in the positive reviews. Appointment-scheduling and follow-ups, wait-times, costs, virtual experience and professional expertise were important factors in the negative reviews. Discussion: To improve the overall experience of patients in video-visits, providers need to engage in clear communication, grow excellent bedside and webside manners, promptly attend the video-visit with minimal delays and follow-up with patients after the visit.
RESUMEN
In this paper, the perception of COVID-19 situation amongst coaching, mentoring, and supervision practitioners is analyzed based on the survey conducted by European Mentoring Coaching Council (EMCC Global) with the participation of (476) people from various countries. Based on the data obtained, ‘word cluster analysis-emotional text mining' and ‘correlation analysis' are performed. The major empirical findings are summarized as follows: firstly, correlations are calculated among the most repetitive words in the statements of participants by using the Euclidian distance approach. In this respect, participants describe COVID-19 related feelings with the most frequent words they use as coaching, work, anxiety, clients, working, fear, time, business, home, and stress respectively. This indicates that COVID-19 epidemic related issues leads participants to think about their clients. They have the most common feelings of anxiety, stress, and fear at work, business and home. They are sensitive about the time as well. Secondly, cluster dendrogram is applied and this indicates that there are five major categories defined with strong correlation between them such that: coaching, work, anxiety, change, issues, crisis, will, managing, new, people, management, client, working, fear, uncertainty, future, time, stress, business, home. In conclusion, policy recommendations are made regarding the pandemic period all over the world in order to contribute relevant literature based on the empirical findings of EMCC Global's survey. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
RESUMEN
Inequalities and exclusion from education were exposed and worsened during the COVID-19 pandemic;however, it forced us to recognize the need to make equality, equity, and social inclusion policies effective for all. Scientific and technological solutions to global threats depend on the formation of the maximum number of qualified human resources, which entirely relies on enabling everyone to acquire, update, and improve their knowledge, skills, and competencies through lifelong learning and higher education. To guarantee inclusive and quality education for all (UN Sustainable Development Goal 4) is hard to achieve at higher education or post-secondary levels. This research aims to provide an overview of the achievements and challenges that higher education institutions (HEI) face in fulfilling the requirements of students with disabilities (SWD). We analyzed a database of 104 s from reviews of SWD in HEI published in Scopus-indexed journals between 2018 and August 2022. After data preprocessing, the text mining analysis on the corpus was visualized in word clouds and graphs. From the results, we could identify that providing access to facilities and information still dominates the research on inclusive education, and visual disability is the most frequently analyzed. The graphs reveal published research on undergraduates with disorders like Autism Spectrum (ASD), learning disorders, and visual, hearing, physical, intellectual, and psychosocial disabilities. The authors also evidenced the lack of information on the barriers and needs of SWD in HEI and potential future research to address them. Concerning the strategies to attend and care for SWD inside the classrooms, the graphs highlight Universal Design as a promising trend leading to inclusivity in higher education. The results and analyses in current research provide essential information to educational stakeholders and decision-makers inside institutions so that they can take action to embrace diversity. © 2023 IEEE.
RESUMEN
Recent studies in machine learning have demonstrated the effectiveness of applying graph neural networks (GNNs) to single-cell RNA sequencing (scRNA-seq) data to predict COVID-19 disease states. In this study, we propose a graph attention capsule network (GACapNet) which extracts and fuses Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) transcriptomic patterns to improve node classification performance on cells and genes. Significantly different from the existing GNN approaches, we innovatively incorporate a capsule layer with dynamic routing into our model architecture to combine and fuse gene features effectively and to allow those more prominent gene features present in the output. We evaluate our GACapNet model on two scRNA-seq datasets, and the experimental results show that our GACapNet model significantly outperforms state-of-the-art baseline models. Therefore, our study demonstrates the capability of advanced machine learning models to generate predictive features and evolutionary patterns of the SARS-CoV-2 pathogen, and the applicability of closing knowledge gaps in the pathogenesis and recovery of COVID-19. © 2022 IEEE.
RESUMEN
Social media has shown to affect tourist activity and spending. However, research related to travel intentions from a large-scale perspective has remained very limited in Indonesia. This research presents an empirical case study using the text mining process on Indonesian domestic tourists' travel intentions to fill in the missing gap. Text classification was used to categorize whether a tweet includes travel intentions or not by concentrating on tourism-related tweet data from Twitter before and after the COVID-19 pandemic. The process of entity recognition was also used to classify the entities in the Tweet. This study showed that the Indonesian intention to travel was 13.08 percent higher than before the pandemic of COVID-19. Moreover, it was also found that interest in adventure activities increased by 581.25 percent and honeymoon trips by 175 percent. Surprisingly, 92 percent of short-stay intentions concluded in this research. However, Indonesian tourists who want to take a long tour are rising by 215.18 percent. This study's findings also show Indonesian tourists' choice to fly to many destinations, such as Bali, the Riau Islands, and Bandung. A more successful Indonesian tourism promotion strategy is expected to develop as a result of this research. Referring to the study findings, it appears that the current model of promotion is relatively distinct from the existing one. The promotional activities that emphasize and focus on 1) sustainable growth, 2) improved productivity, 3) investment innovation and digital transformation, 4) morals, culture, and social responsibility, and 5) technological cooperation has become increasingly important to be incorporated in various programs by The Ministry of Tourism of Indonesia. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2022.
RESUMEN
The COVID-19 pandemic has been accompanied by a proliferation of online misinformation and disinformation about the virus. Combating this 'infodemic' has been identified as one of the top priorities of the World Health Organization, because false and misleading information can lead to a range of negative consequences, including the spread of false remedies, conspiracy theories, and xenophobia. This paper aims to combat the COVID-19 infodemic on multiple fronts, including determining the credibility of information, identifying its potential harm to society, and the necessity of intervention by relevant organizations. We present a prompt-based curriculum learning method to achieve this goal. The proposed method could overcome the challenges of data sparsity and class imbalance issues. Using online social media texts as input, the proposed model can verify content from multiple perspectives by answering a series of questions concerning the text's reliability. Experiments revealed the effectiveness of prompt tuning and curriculum learning in assessing the reliability of COVID-19-related text. The proposed method outperforms typical text classification methods, including fastText and BERT. In addition, the proposed method is robust to the hyperparameter settings, making it more applicable with limited infrastructure resources.
RESUMEN
Under the influence of the health emergency triggered by the COVID-19 pandemic, many brands changed their communication strategy and included more or less explicit references to the principles of solidarity and fraternity in their TV commercials to boost the confidence and hope of Italian families during the lockdown. The traditional attitudes of the advertising format, which focused on product characteristics, were relegated to the background in order to reinforce the "brand image" through words, signs, hashtags and music that spread empathetic messages to all those who needed to regain hope and trust in a time of extreme emotional fragility. The objective of this paper is to identify the emotions and brand awareness during the lockdown using text mining techniques by measuring customer sentiment expressed on the Twitter social network. Our proposal starts from an unstructured corpus of 20,982 tweets processed with text data mining techniques to identify patterns and trends in people's posts related to specific hashtags and TV ads produced during the COVID-19 pandemic. The innovations in the brand's advertising among consumers seem to have triggered some sense of appreciation and gratitude, as well as a strong sense of belonging that was not present before, as the TV ads were perceived as a disruptive element in consumers' tweets. Although this effect is clearly documented, in this paper we demonstrate its transitory nature, in the sense that the frequency of occurrence of terms associated with an emotional dimension peaks during the weeks of lockdown, and then gradually decreases.
RESUMEN
This paper combines available NLP technologies for Serbian languages and traditional data science methods in order to analyze collected dataset on the news headlines related to the COVID-19 pandemics. As an addition to NLP technologies for the Serbian language, a specialized database was created in an attempt to enhance the research within the field. Within the paper, the database was exploratory analyzed, and perspectives of the work with the data were thoroughly explored. © 2023 IEEE.
RESUMEN
Opportunities to participate in physical activities (PA) and fitness exercises in public and private facilities have been reduced or banned due to social distancing regulations during the height of the global pandemic. Though Korea has not experienced lockdown, several venues have been restricted to prevent the spread of Covid-19. Despite the limitations of PA engagement, people have found alternative activities by using online platforms to keep active and fit. Thus, this study focuses on analyzing fitness-related video titles from YouTube. By collecting data through text mining and conducting network analysis, it provides basic knowledge of the fitness trends from pre- and post-Covid-19. As a result, ‘exercise' was found to have the highest tendency and had strong connections to keywords that indicated specific methods of working out to become fit, but it also had connections to trendy keywords such as ‘hip-up' and ‘body-profile' which reflect the fitness culture in Korea.
RESUMEN
As the COVID-19 pandemic motivated a shift to virtual teaching, exams have increasingly moved online too. Detecting cheating through collusion is not easy when tech-savvy students take online exams at home and on their own devices. Such online at-home exams may tempt students to collude and share materials and answers. However, online exams' digital output also enables computer-aided detection of collusion patterns. This paper presents two simple data-driven techniques to analyze exam event logs and essay-form answers. Based on examples from exams in social sciences, we show that such analyses can reveal patterns of student collusion. We suggest using these patterns to quantify the degree of collusion. Finally, we summarize a set of lessons learned about designing and analyzing online exams. Copyright: © 2021 The Author(s).
RESUMEN
The COVID-19 pandemic has deeply affected the airline industry, as it has many sectors, and has created tremendous financial pressure on companies. Flight bans, new regulations, and restrictions increase consumer complaints and are emerging as a big problem for airline companies. Understanding the main reasons triggering complaints and eliminating service failures in the airline industry will be a vital strategic priority for businesses, while reviewing the dimensions of service quality during the COVID-19 pandemic provides an excellent opportunity for academic literature. In this study, 10,594 complaints against two major airlines that offer full-service and low-cost options were analyzed with the Latent Dirichlet Allocation algorithm to categorize them by essential topics. Results provide valuable information for both. Furthermore, this study fills the gap in the existing literature by proposing a decision support system to identify significant service failures through passenger complaints in the airline industry utilizing e-complaints during an unusual situation such as the COVID-19 pandemic.
RESUMEN
The use of technologies that provide objective, digital data to clinicians, carers, and service users to improve care and outcomes comes under the unifying term Digital Health. This field, which includes the use of high-tech health devices, telemedicine and health analytics has, in recent years, seen significant growth in the United Kingdom and worldwide. It is clearly acknowledged by multiple stakeholders that digital health innovations are necessary for the future of improved and more economic healthcare service delivery. Here we consider digital health-related research and applications by using an informatics tool to objectively survey the field. We have used a quantitative text-mining technique, applied to published works in the field of digital health, to capture and analyse key approaches taken and the diseases areas where these have been applied. Key areas of research and application are shown to be cardiovascular, stroke, and hypertension; although the range seen is wide. We consider advances in digital health and telemedicine in light of the COVID-19 pandemic.
RESUMEN
In most biomedical research paper corpus, document classification is a crucial task. Even due to the global epidemic, it is a crucial task for researchers across a variety of fields to figure out the relevant scientific research papers accurately and quickly from a flood of biomedical research papers. It can also assist learners or researchers in assigning a research paper to an appropriate category and also help to find the relevant research paper within a very short time. A biomedical document classifier needs to be designed differently to go beyond a "general" text classifier because it's not dependent only on the text itself (i.e. on titles and abstracts) but can also utilize other information like entities extracted using some medical taxonomies or bibliometric data. The main objective of this research was to find out the type of information or features and representation method creates influence the biomedical document classification task. For this reason, we run several experiments on conventional text classification methods with different kinds of features extracted from the titles, abstracts, and bibliometric data. These procedures include data cleaning, feature engineering, and multi-class classification. Eleven different variants of input data tables were created and analyzed using ten machine learning algorithms. We also evaluate the data efficiency and interpretability of these models as essential features of any biomedical research paper classification system for handling specifically the COVID-19 related health crisis. Our major findings are that TF-IDF representations outperform the entity extraction methods and the abstract itself provides sufficient information for correct classification. Out of the used machine learning algorithms, the best performance over various forms of document representation was achieved by Random Forest and Neural Network (BERT). Our results lead to a concrete guideline for practitioners on biomedical document classification.
RESUMEN
First, some electoral processes and then the COVID-19 crisis have brought offensive and dangerous disinformation events in social media into the spotlight. This research analyses an event concerning disinformation and the launch and dissemination of the hashtag #ExposeBillGates, through the 183,016 tweets that used this hashtag during its period of activity in June 2020. Through network analysis and by processing the content of the messages through text mining, it was observed that the size of the event was highly dependent on the participation of a small number of accounts, and some violent and abusive communication was found, although not hate speech. The need to deeply study the relations-hip between two macro communicative phenomena of a different nature, but more intertwined in their "problematic" origin than may appear, is discussed.
RESUMEN
China has recently declared its role as a leading developing country in actively practicing carbon neutrality. In fact, its carbon-neutral policy has accelerated from a gradual and macroscopic perspective and has been actively pursued given the changes not only in the overall social system but also in its impact on various stakeholders. This study analyzed the patterns of carbon neutrality (CN) and the actors of policy promotion in China from a long-term perspective. It collected policy discourses related to CN posted on Chinese websites from 2000 to 2022 and conducted text mining and network analysis. The results revealed that the pattern of CN promotion in China followed an exploration-demonstration-industrialization-digitalization model, similar to other policies. Moreover, the policy promotion sector developed in the direction of unification-diversification-specialization. Analysis of policy promotion actors found that enterprises are the key driver of continuous CN. In addition, the public emerged as a critical actor in promoting CN during the 12th-13th Five-Year Plans (2011-2020). Moreover, the central government emerged as a key driving actor of CN during the 14th Five-Year Plan. This was a result of the emphasis on efficiency in the timing and mission process of achieving CN. Furthermore, based on the experience of COVID-19, the rapid transition of Chinese society toward CN emphasizes the need for a central government with strong executive power. Based on these results, this study presents constructive suggestions for carbon-neutral development in China.
RESUMEN
MOOCs can be considered as a powerful alternative in extraordinary situations where people cannot reach formal education. In recent years, the widespread use of the internet worldwide and especially the CoVID-19 has increased the need of people for MOOCs. However, in order to increase the effectiveness of MOOCs, and to provide a better learning environment, the need to evaluate MOOCs has arisen. One of the indicators of quality in online learning is student satisfaction. Accordingly, this research aims to reveal learner satisfaction in MOOCs. The most important indicator for measuring this satisfaction in MOOCs is user comments. In this study, 39101 comments of the participants in 960 MOOCs were examined by using text mining techniques within the framework of satisfaction.