Search

This article introduces an artificial intelligence (AI)‐based system for forecasting food insecurity in data‐limited settings, employing unsupervised neural networks for topic modeling on news data. Unlike traditional methods, our system operates without relying on expert assumptions about food insecurity factors. Through a case study in Somalia, we show that the method can yield competitive performance, even in the absence of traditional food security indicators such as food prices. This system is valuable in supporting expert assessments of food insecurity, unlocking a wealth of untapped information from news outlets, and offering a path toward more frequent and automated food insecurity monitoring for timely crisis intervention. [ABSTRACT FROM AUTHOR]

Copyright of Folklor / Edebiyat is the property of Cyprus International University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Natural disasters leave scenes of devastation in their wake upon arrival. Sometimes, the destruction is so prominent that reaching the area where the disaster happened becomes challenging-rescuing and communicating with the victims and providing relief become nearly impossible. Nevertheless, some people continuously try to post about the situation on social media, like Facebook. Moreover, the Mass Media utilized the latest technology to search for the latest updates on the impacted area. Analyzing the social and mass media to be aware of the situation can help the authorities take necessary steps. In this research, we intend to develop a multilingual (Bangla and English) system that can predict the post-disaster impact by maneuvering the contents from mass and social media. Therefore, we have created a novel multilingual dataset using the disaster news from Newspaper and posts from Facebook and utilized the modern text processing architecture transformers. For Bangla and English news and posts, our proposed mBERT model achieved accuracy of 89.38 and 87.80%, respectively. [ABSTRACT FROM AUTHOR]

Blockchain Technology (BCT) offers several possible applications in the field of electronic commerce (e-commerce), such as decentralised marketplaces or payments in cryptocurrencies. Even though these applications of BCT have already been explored in the academic literature, a comprehensive collection along the whole e-commerce value chain is still missing. Furthermore, the existing comprehensive reviews are based on the academic literature whilst the evolution and further development of BCT is highly driven by practitioners. Therefore, we aim to understand how and why BCT is used in e-commerce based on a qualitative content analysis of news articles, i.e., we apply scientific methods to content which reports the latest developments in the field. As a result, we describe the multiple application domains of BCT along the e-commerce value chain. Subsequently, we discuss the main underlying principles of BCT usage across all the value chain steps. [ABSTRACT FROM AUTHOR]

Child marriage, specifically the marriage of underage girls, is a crucial social problem that cuts across religions and cultures and can be considered as violence against children and women. Currently, the media is one of the strongest public spheres to combat this problem apart from national and international laws and agreements. This study aims to analyse how the child marriage problem is represented in the Turkish print media within the framework of feminist theory. The analysis is based on 246 news reports related to child marriages. The study found that even though the issue has been identified as a problem in the Turkish print media, it has not come to the forefront. Rather, the newspapers have normalized the issue of underage marriage, especially through the use of language. [ABSTRACT FROM AUTHOR]

Wisconsin's Driftless Area, an unglaciated region defined by steep river valley systems, has been plagued by chronic flooding in part due to Euro-American agricultural practices and anthropogenic climate change. The region, which has played a central role in environmental knowledge production, has a storied history of resilience practices and flood experience. To capture histories of Driftless Area flood experience and underlying socio-ecological dynamics, we performed a qualitative analysis of regional news archives from 1866 to present on flood trends, experiences, and responses. Our analysis identified hazard response trends mediated by socio-ecological factors including crisis-induced windows of opportunity for change, conflicts over structural and nonstructural responses to flooding, and psychological dimensions of environmental crises. Finally, our analysis noted the key role of community flood knowledge in producing shifts toward enhanced resilience, suggesting the need for empowering flood response planning at the community scale. [ABSTRACT FROM AUTHOR]

Blasphemy is a significant and sensitive topic in the news, prompting mass media to allocate coverage to religious issues. This study utilizes qualitative methods, employing the framing model analysis of William A. Gamson and Andre Modigliani. The objective is to examine news concerning alleged blasphemy cases involving Panji Gumilang, the head of Al-Zaytun ponpes, as reported by Republika and Detik during the period from July to August 2023. Researchers scrutinized six news articles, three from Republika and three from Detik. The findings reveal that both Republika and Detik distinctly highlight ongoing investigations by law authorities into the blasphemy case attributed to Panji Gumilang. Republika's coverage primarily focuses on evidence exploration to gather information, reinforcing the report on the alleged blasphemy case for a smoother legal process and justice. In contrast, Detik examines the societal influence and impact of the blasphemy case. Meanwhile, Detik discussed the influence and impact of this blasphemy case on society. The reason for choosing the two media is because both have different backgrounds, Republika is a media born from the Muslim community that is more in-depth in news related to Islamic religious issues while Detik is a popular media whose reporting is neutral. [ABSTRACT FROM AUTHOR]

In order to increase the effectiveness of medical care and adapt to Industry 4.0 technologies, it becomes necessary to determine the current directions of healthcare development. The study purpose is to identify trends and development patterns of innovative technologies in the field of healthcare using data mining methods. The research methodology is based on the methods’ application of information messages’ text analysis. The data set was formed by parsing publications from Google RSS feeds and PubMed database for the period 2018–2022. To analyze the generated data sets, a dynamic modification of the BERTopic natural language processing model and the Bibliometrix library were used. To assess the differences in the structure of publications in the annual section, the Wilcoxon T-test was applied. The data sets contain 10,307 informational messages from leading publishers and 4,673 scientific publications. Four most relevant areas of research for the healthcare sector have been identified: 1) adaptive management in the field of healthcare; 2) information technologies in healthcare; 3) resource provision of medical organizations; 4) medical care for diseases. The most actively developing direction is related to the use of information technology. The number of publications on this issue in 2022 increased by 137.42% compared to 2020. The main areas of research are the development of medical CRM systems, the use of information technologies both for the development of tools for combating pandemics, and for methods of quality management and lean manufacturing. The study results can be used to improve the quality of medical care to the population of Russia.

In the analysis of scientific and pedagogical approaches to news literacy, two fundamentally different areas of research have been identified: practice-oriented and comprehensive. The origins, essence, subject field, and crucial concepts of library and information approach to news literacy are elaborated. The institutionalization patterns of news literacy within the framework of library and information activities have been identified and discussed. The experience of designing an educational discipline on the analysis of news is characterized, and original analytical technology for deconstructing news messages is presented. [ABSTRACT FROM AUTHOR]

News impact analysis has become a common task conducted by finance researchers, which involves reading and selecting news articles based on themes and sentiments, pairing news events and relevant stocks, and measuring the impact of selected news on stock prices. To facilitate more efficient news selection, topic modeling can be applied to generate topics out of a large number of news documents. However, there is very limited existing literature comparing topic models in the context of finance-related news impact analysis. In this paper, we compare three state-of-the-art topic models, namely Latent Dirichlet allocation (LDA), Top2Vec, and BERTopic, in a defined scenario of news impact analysis on financial markets, where 38,240 news articles with an average length of 590 words are analyzed. A service-oriented framework for news impact analysis called "News Impact Analysis" (NIA) is advocated to leverage multiple topic models and provide an automated and seamless news impact analysis process for finance researchers. Experimental results have shown that BERTopic performed best in this scenario, with minimal data preprocessing, the highest coherence score, the best interpretability, and reasonable computing time. In addition, a finance researcher was able to conduct the entire news impact analysis process, which validated the feasibility and usability of the NIA framework. [ABSTRACT FROM AUTHOR]

The analysis of news dissemination is of utmost importance since the credibility of information and the identification of disinformation and misinformation affect society as a whole. Given the large amounts of news data published daily on the Web, the empirical analysis of news with regard to research questions and the detection of problematic news content on the Web require computational methods that work at scale. Today's online news are typically disseminated in a multimodal form, including various presentation modalities such as text, image, audio, and video. Recent developments in multimodal machine learning now make it possible to capture basic “descriptive” relations between modalities–such as correspondences between words and phrases, on the one hand, and corresponding visual depictions of the verbally expressed information on the other. Although such advances have enabled tremendous progress in tasks like image captioning, text-to-image generation and visual question answering, in domains such as news dissemination, there is a need to go further. In this paper, we introduce a novel framework for the computational analysis of multimodal news. We motivate a set of more complex image-text relations as well as multimodal news values based on real examples of news reports and consider their realization by computational approaches. To this end, we provide (a) an overview of existing literature from semiotics where detailed proposals have been made for taxonomies covering diverse image-text relations generalisable to any domain; (b) an overview of computational work that derives models of image-text relations from data; and (c) an overview of a particular class of news-centric attributes developed in journalism studies called news values. The result is a novel framework for multimodal news analysis that closes existing gaps in previous work while maintaining and combining the strengths of those accounts. We assess and discuss the elements of the framework with real-world examples and use cases, setting out research directions at the intersection of multimodal learning, multimodal analytics and computational social sciences that can benefit from our approach.

Aim: To investigate workplace violence in online articles and compare workplace violence‐related words characteristics of nurses and other professionals using social network analysis. Background: Workplace violence is a widespread problem across nursing practice. Online articles are useful for the timely identification and management of nurse violence problems. Methods: This descriptive exploratory study involved data extraction focused around the search term workplace violence from sources published during January 1990–December 2020 listed in the BIGKinds database, a Korean integrated news database system. The connections between the extracted terms were determined through social network analysis using the software UCINET and NetDraw. Results: Our search found 675 articles for nurses and 5797 articles for other professionals related to workplace violence. Work burden was found to be the primary cause of violence among both nurses and other professionals. Specifically, being a woman was closely related to violence among nurses, and abuse of power was closely related to violence among other professionals. Conclusion: Nurses and other professionals have different vulnerabilities to violence, which require a different approach to addressing violence. Implications for Nursing Management: Nurse managers should provide a healthy work environment, sufficient workforce and flexible work schedules to protect nurses from workplace violence. [ABSTRACT FROM AUTHOR]

The climate crisis, natural resource exploitation, and concerns around how to feed a growing world population have resulted in a growing chorus identifying the need for a Plan B. For some, this Plan B entails preparing for long-duration space missions and the development of human settlement on Mars. To plan for long-duration space missions, the development of food production technologies that can withstand extreme conditions such as poor soil, lack of gravity, and radiation are increasingly prioritized. These technologies may include genetic engineering, digital agriculture, 3D bioprinting, synthetically grown meat and more. Government and corporate proponents of long-duration space missions—NASA and SpaceX, among others—are actively funding agricultural research in space. They argue that the technologies developed for space will have positive implications beyond Mars—directly benefitting Earth and its inhabitants. This paper demonstrates that news reporting on the technology has been overall uncritical. Media narratives surrounding issues of food growth in space have not been studied. This study analyzes how English news media coverage (n = 170) from 67 publications report the feasibility of long-duration space missions, human settlements, and high-tech agricultural technologies. We provide a cross-section of the types of agricultural technologies being covered, the key organizations and actors in the field, and a critical analysis of media narratives. Using mixed methods content and discourse analysis, this study finds that the news media publications overwhelmingly portray long-duration space missions as both inevitable and a positive good for humanity. Without critically assessing the societal implications of food technologies for long-duration space missions vis-à-vis their benefits on Earth, we risk glossing over systemic and structural inequalities in the food system.

Haber metinlerinin olayları aktarırken liberal anlayışın gereği olarak ayna vazifesi görmesi ve tarafsız aktarımda bulunması beklenmektedir. Ancak basın kuruluşlarının zaman zaman devletlerin ideolojik aygıtları işlevini üstlenerek devletin sahip olmuş olduğu ideolojiyi yeniden ürettiğine de rastlanmaktadır. Basın kuruluşlarının ideolojiyi yeniden üretiminde pek çok farklı unsur devreye girmektedir. Ekonomik veya siyasi bağlılıkların yanında kültür, kimlik veya dini sebeplerde ideolojik yakınlığın sebepleri olabilmektedir. Bu kapsamda Türkiye-Azerbaycan arasındaki ilişkinin tarihsel, kültürel, dini veya dil gibi ortak yönleri ışığında ve Türkiye-Ermenistan arasındaki ilişkide de tarihsel ardalan devletin ideolojisini belirlemekte önemli rol üstlenmektedir. Bu bağlamda Azerbaycan-Ermenistan arasında Karabağ bölgesinde süren çatışmaların ideolojinin bu etkileri çerçevesinde Cumhuriyet ve Sabah Gazetelerine yansıması van Dijk’ın söylem çözümlemesi modeli uygulanarak incelenmiştir. Çalışma sonunda, Türkiye’nin Karabağ sorununda ve Azerbaycan konusunda sahip olduğu ideolojik kabulün her iki gazete tarafından da yansıtıldığı ortaya çıkmıştır. Ancak birkaç nadir haberde Cumhuriyet Gazetesi alternatif söylemleri dile getirmeye çalışmıştır. Böylece basının devletin ideolojik aygıtı olarak rol üstlendiği ve 4. güç işlevini yerine getiremediği görülmüştür.

Copyright of Universitas, Revista de Ciencias Sociales y Humanas is the property of Universidad Politecnica Salesiana and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

As a result of the COVID-19 pandemic, libraries in China closed their doors in early 2020 and moved all their services online. This change has brought unprecedented challenges for the development of library services, while it has also brought opportunities and motivation for the future transformation of libraries. This article uses official WeChat accounts of the National Library of China and more than 30 provincial public libraries as the main information sources to summarize and classify the services provided during the period of closure. It also collates and analyses news items released by these libraries to guide the improvement of the online services of public libraries in the pandemic environment. Finally, it puts forward the author's reflections and suggestions on the key development directions of libraries in the post-pandemic era in six areas: reading promotion, smart libraries, new media operation, information literacy cultivation, open access and collaborative development. [ABSTRACT FROM AUTHOR]

Copyright of Turkish Online Journal of Design, Art & Communication is the property of Turkish Online Journal of Design, Art & Communication and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The data article presents a dataset and a tool for news-based monitoring of sustainable development goals defined by the United Nations. The presented dataset was created by structured queries of the GDELT database based on the categories of the World Bank taxonomy matched to sustainable development goals. The Google BigQuery SQL scripts and the results of the related network analysis are attached to the data to provide a toolset for the strategic management of sustainability issues. The article demonstrates the dataset on the 6th sustainable development goal (Clean Water and Sanitation). The network formed based on how countries appear in the same news can be used to explore the potential international cooperation. The network formed based on how topics of World Bank taxonomy appear in the same news can be used to explore how the problems and solutions of sustainability issues are interlinked.

In the current age of overwhelming information and massive production of textual data on the Web, Event Detection has become an increasingly important task in various application domains. Several research branches have been developed to tackle the problem from different perspectives, including Natural Language Processing and Big Data analysis, with the goal of providing valuable resources to support decision-making in a wide variety of fields. In this paper, we propose a real-time domain-specific clustering-based event-detection approach that integrates textual information coming, on one hand, from traditional newswires and, on the other hand, from microblogging platforms. The goal of the implemented pipeline is twofold: (i) providing insights to the user about the relevant events that are reported in the press on a daily basis; (ii) alerting the user about potentially important and impactful events, referred to as hot events, for some specific tasks or domains of interest. The algorithm identifies clusters of related news stories published by globally renowned press sources, which guarantee authoritative, noise-free information about current affairs; subsequently, the content extracted from microblogs is associated to the clusters in order to gain an assessment of the relevance of the event in the public opinion. To identify the events of a day d we create the lexicon by looking at news articles and stock data of previous days up to d−1 Although the approach can be extended to a variety of domains (e.g. politics, economy, sports), we hereby present a specific implementation in the financial sector. We validated our solution through a qualitative and quantitative evaluation, performed on the Dow Jones’ Data, News and Analytics dataset, on a stream of messages extracted from the microblogging platform Stocktwits, and on the Standard & Poor’s 500 index time-series. The experiments demonstrate the effectiveness of our proposal in extracting meaningful information from real-world events and in spotting hot events in the financial sphere. An added value of the evaluation is given by the visual inspection of a selected number of significant real-world events, starting from the Brexit Referendum and reaching until the recent outbreak of the Covid-19 pandemic in early 2020.

This study aims to bring about a novel approach to the analysis of Sustainable Development Goals (SDGs) based solely on the appearance of news. Our purpose is to provide a monitoring tool that enables world news to be detected in an SDG-oriented manner, by considering multilingual as well as wide geographic coverage. The association of the goals with news basis the World Bank Group Topical Taxonomy, from which the selection of search words approximates the 17 development goals. News is extracted from The GDELT Project (Global Database of Events, Language and Tone) which gathers both printed as well as online news from around the world. 60 851 572 relevant news stories were identified in 2019. The intertwining of world news with SDGs as well as connections between countries are interpreted and highlight that even in the most SDG-sensitive countries, only 2.5% of the news can be attributed to the goals. Most of the news about sustainability appears in Africa as well as East and Southeast Asia, moreover typically the most negative tone of news can be observed in Africa. In the case of climate change (SDG 13), the United States plays a key role in both the share of news and the negative tone. Using the tools of network science, it can be verified that SDGs can be characterized on the basis of world news.This news-centred network analysis of SDGs identifies global partnerships as well as national stages of implementation towards a sustainable socio-environmental ecosystem. In the field of sustainability, it is vital to form the attitudes and environmental awareness of people, which strategic plans cannot address but can be measured well through the news.

This paper is to identify the recent growing crisis from coronavirus infections-19, using domestic news big data. This paper analyzed media articles related to the crisis caused by COVID-19 using the Korea Press Foundation's news big data analysis system 'BIGKinds'. In this paper, a total of 54 media articles were extracted around the keywords 'Corona' and 'Crisis', after a period of about 10 months. We want to understand the correlation coefficient between the two keywords "Corona" and "Crisis" and to understand what kind of crisis the COVID-19 is facing for each representative category of economy, society, international and cultural. As the COVID-19 crisis is taking a heavy toll on the economy, society and any other categories, this research using big data is expected to be used as a basic data to overcome the crisis of COVID-19. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Al-Frahids Arts is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The study examined the news frames embedded in the news regarding the investment deal between the state of Wisconsin and Foxconn in 2017. The deal had generated a considerable amount of debate, especially in the state of Wisconsin since it was the largest-ever subsidy for the state of Wisconsin to have a company invest in the state and the largest government handout to a foreign company ever given in the U.S. A qualitative content analysis on Wisconsin daily newspapers was used to identify the news frames. Five news frames were identified: financial cost/economic growth, risk/government responsibility, transformational opportunity, conflict, and fairness and justice. By examining the news frames embedded in the news stories, this study revealed not only what voices and powers for the 2017 Wisconsin and Foxconn investment deal have been competing in the news discourse, but also how the different voices were addressed in the news discourse. [ABSTRACT FROM AUTHOR]

The determination of the firm life cycle has been carried out in relation to the establishment of corporate strategy in the field of accounting or management. The life cycle prediction based on financial information is long because it is determined based on the financial performance of the entity over a year. This study sought to lay the foundation for overcoming this by using news articles to predict the life cycle of a company. In the process of quantifying news article data and predicting the firm life cycle, the method of selecting keywords that can represent the firm life cycle is presented, and the life cycle prediction model is verified with four machine learning techniques using selected candidate keywords. In this study, all four machine learning techniques showed a predicted static classification rate of nearly 60%, demonstrating the availability of news articles, which are unstructured text data, in predicting the corporate life cycle.

The data article presents a dataset suitable to measure regional Industry 4.0 (I4.0+) readiness. The I4.0+ dataset includes 101 indicators with 248 958 observations, aggregated to NUTS 2 statistical level) based on open data in the field of education (ETER, Erasmus), science (USPTO, MA-Graph, GRID), government (Eurostat) and media coverage (GDELT). Indicators consider the I4.0-specific domain of higher education and lifelong learning, innovation, technological investment, labour market and technological readiness as indicators. A composite indicator, the I4.0+ index was constructed by the Promethee method, to identify regional rank regarding their I4.0 performance. The index is validated with economic (GDP) and innovation indexes (Regional Innovation Index).

Haber metinlerinin, sosyal mekanizmaları toplum adına gözetleyen ve şeffaf olarak sunan bir yapıya sahip olduğu düşünülmektedir. Ancak bu durum egemen gücün medyayı tekeline almasıyla birlikte uzun sürmemiş ve haber üreticilerine ele aldıkları konuları meşrulaştırıcı bir güç vermiştir. Eleştirel yaklaşımlar ise, iktidarın medya aracılığı ile gerçekleştirdiği bu meşrulaştırmaya karşı çıkmaktadır. Medya metinlerinin, haberlerin toplumsal iktidarın kurulmasındaki rolü söylem çözümlemesi ile sunulmaya çalışılmaktadır. Söylem çözümlemesi ile dilin ve temsilin nasıl üretildiğinin yanı sıra, temsil, anlam, iktidar arasındaki ilişkiler, kimlikler ve öznelliklerin oluşumu incelenmektedir. Eleştirel söylem analizi, güç, hâkimiyet, hegomanya, sınıf farkı, cinsiyet, ırk, ideoloji, ayrımcılık, çıkar, kazanç, yeniden oluşturma, dönüştürme, gelenek, sosyal yapı ya da sosyal düzen gibi temaları ön plana çıkaran ve araştırma alanı olarak bu konuları işleyen söylem analizi yöntemidir. Bu bağlamda çalışma, Türkiye’de öldürülen İtalyan sanatçı Giuseppina Pasqualino (Pippa Bacca) ile ilgili yazılı basında çıkan haberlerin farklı gazetelerde eleştirel söylem çözümlemesi açısından ne şekilde ele alındığını incelemek amacıyla oluşturulmuştur. Çalışma kapsamında Teun A. van Dijk’ın eleştirel söylem çözümlemesi modeli kullanılmıştır. Van Dijk, eleştirel söylem analizinde sosyobilişsel yaklaşımının kurucusudur, bu yaklaşım eleştirel söylem çözümlemesinin sosyo psikolojik yönüne aittir ve sosyal temsil kuramına dayanmaktadır. Van Dijk; biliş, söylem ve toplum arasında etkileşim kurmaktadır ve güce erişim sağlama araçları olarak söylemin kontrolüne odaklanmaktadır. Daha çok stereotipleşme, etnik kötüye kullanım ve egemen gruplara direnme ile ilgilenmektedir.

As "mukbang" (eating broadcast) becomes increasingly widespread, there is growing interest about the impact of mukbang on public health. This study aimed to analyze the content of mukbang YouTube videos, as well as news articles related to mukbang and the association between watching mukbang videos and health habits. We analyzed 5952 YouTube mukbang videos, 5265 news articles, and a survey of 1200 people in Korea. In this study, we confirmed that the provocative content of mukbang YouTube videos, such as overeating, was related to video popularity (p < 0.001). In addition, more exposure to mukbang was associated with greater effects on dietary health due to mukbang (p < 0.001). The prevalence of news articles on the negative effects of mukbang showed an increasing trend over time, while the articles on "Mukbang is funny" were most common in all the years evaluated. To cope with public health problems such as obesity, it will be necessary to continue to investigate the content and effects of mukbang on public health. [ABSTRACT FROM AUTHOR]

In this paper, we address the task of zero-shot cross-lingual news sentiment classification. Given the annotated dataset of positive, neutral, and negative news in Slovene, the aim is to develop a news classification system that assigns the sentiment category not only to Slovene news, but to news in another language without any training data required. Our system is based on the multilingual BERTmodel, while we test different approaches for handling long documents and propose a novel technique for sentiment enrichment of the BERT model as an intermediate training step. With the proposed approach, we achieve state-of-the-art performance on the sentiment analysis task on Slovenian news. We evaluate the zero-shot cross-lingual capabilities of our system on a novel news sentiment test set in Croatian. The results show that the cross-lingual approach also largely outperforms the majority classifier, as well as all settings without sentiment enrichment in pre-training. [ABSTRACT FROM AUTHOR]

BACKGROUND: Covaxin is the first indigenous vaccine developed in India against COVID-19. The purpose of this study was to analyze the news stories on Covaxin published in the online media between two statements issued by Indian Council for Medical Research on 2nd and 4th July for their content, quality of information, and reporting standards. MATERIALS AND METHODS: A systematic search was performed on Google to identify the news stories related to Covaxin in the English language published between these two statements. The selected news stories were subjected to content analysis and reviewed using the screening points developed through a consultation by two independent experts using ten prevalidated criteria for health news review. The data were analyzed in MS Excel and StataMP14. RESULTS: The final analysis included 24 news stories. The mean and median score of the news stories is 10.71 and 12 (out of 20), respectively, with a score ranging from 2 to 17. The stories did not promote disease or vaccine mongering (100%), adequately mentioned the true novelty of the vaccine (95.8%), and source of the information (83.3%). However, they mostly failed to mention the information on costs, research data related to benefits, and harms and quality of the available evidence. CONCLUSION: There is a lack of reporting of detailed analysis about the methodology of development of the vaccine and limitations in its research design by health journalists. It is important to train journalists on proper reporting of health news to improve its quality in Indian media.

In this paper, we address the task of zero-shot cross-lingual news sentiment classification. Given the annotated dataset of positive, neutral, and negative news in Slovene, the aim is to develop a news classification system that assigns the sentiment category not only to Slovene news, but to news in another language without any training data required. Our system is based on the multilingual BERTmodel, while we test different approaches for handling long documents and propose a novel technique for sentiment enrichment of the BERT model as an intermediate training step. With the proposed approach, we achieve state-of-the-art performance on the sentiment analysis task on Slovenian news. We evaluate the zero-shot cross-lingual capabilities of our system on a novel news sentiment test set in Croatian. The results show that the cross-lingual approach also largely outperforms the majority classifier, as well as all settings without sentiment enrichment in pre-training.