Abstract
The impact of the novel coronavirus (COVID-19) is widespread and will likely shape community behavior for months to come. And while the humanitarian and safety-related aspects of this outbreak are top of mind globally, it’s unquestionable that social distancing, quarantining, and staying home will have a significant effect on media consumption, which could rise up to 60%, according to recent research from Nielsen’s U.S. media team. Social media, now a part of everyday life for most consumers engaged with the world digitally, became the primary source for buzz about all things COVID-19 as worries and news intensified. Sentiment analysis is applied in this study to analyze the opinions, feelings, and interests of individuals in the COVID-19. The purpose of this study is to analyze sentiment based on an opinion by classifying individual feelings such as sadness, happiness, or panic in facing a COVID-19 into sentiment level that is negative, positive or, neutral. In this paper, an open-source approach is presented where we have collected tweets from the Twitter API and then reprocessing, analyzing and, visualizing these tweets using python. Furthermore, Twitter data streaming will be processed and cleaned to parse data that can be classified based on opinion with a text mining algorithm using text blob Python. Feature extraction is done for the relationship between words by the Bigram and N-gram methods.
Publisher
STMIK Sinar Nusantara Surakarta
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献