The purpose of this study is to analyse COVID-19 related news published across different geographical places, in order to gain insights in reporting differences. The COVID-19 pandemic had a major outbreak in January 2020 and was followed by different preventive measures, lockdown, and finally by the process of vaccination. To date, more comprehensive analysis of news related to COVID-19 pandemic are missing, especially those which explain what aspects of this pandemic are being reported by newspapers inserted in different economies and belonging to different political alignments. Since LDA is often less coherent when there are news articles published across the world about an event and you look answers for specific queries. It is because of having semantically different content. To address this challenge, we performed pooling of news articles based on information retrieval using TF-IDF score in a data processing step and topic modeling using LDA with combination of 1 to 6 ngrams. We used VADER sentiment analyzer to analyze the differences in sentiments in news articles reported across different geographical places. The novelty of this study is to look at how COVID-19 pandemic was reported by the media, providing a comparison among countries in different political and economic contexts. Our findings suggest that the news reporting by newspapers with different political alignment support the reported content. Also, economic issues reported by newspapers depend on economy of the place where a newspaper resides.
翻译:这项研究的目的是分析不同地理区域发表的COVID-19相关新闻,以便了解报道差异的见解; COVID-19大流行病在2020年1月爆发了一次大规模爆发,随后采取了不同的预防措施,封锁了该流行病,最后是接种过程; 迄今为止,对与COVID-19大流行病有关新闻的更全面分析缺失,特别是那些解释不同经济体和属于不同政治联盟的报纸报道该流行病的各方面内容的报纸正在报道该流行病的报纸; 由于LDA常常不太一致,当世界各地发表关于某一事件的新闻文章时,你会寻找具体查询的答案; 这是因为,COVID-19大流行病的内容存在语义上的差异; 为了应对这一挑战,我们利用TF-IDF的评分,在数据处理步骤和主题上用LDA模型以及1至6ngs的组合,我们用VADER的感知觉分析器分析了在不同地理区域报道的新闻文章中的情绪差异; 这项研究的新颖之处是看媒体报道的COVID-19流行病是如何报道的,为不同政治和经济背景的各国提供了一个比较。