| dc.description.abstract | Over the past decade, the popularity of social data on the internet has seen a rapid growth. This has also in turn resulted in researchers having more access to the data. There has been a steady increase of academic research and commercial use with regards to analyzing social big data. With the outbreak of the global COVID-19 pandemic and the focus of subsequent COVID-19 vaccines, many individuals, media organizations, and governments agencies are pushing information on social media sites.
The purpose of this thesis is to explore the possibility of using social big data and machine learning to help decisionmakers to better understand how people perceives vaccine risk on the social media platforms, and how it can contribute to a better risk communication strategy with regards to vaccine risk. This thesis aims to analysis social big data stored on the social media platform twitter and conduct sentiment analysis to examine the sentiments people have posted on twitter via their tweets that contains the hashtag #vacinne from the period of 1st March 2021 to 31st of March 2021. Further, this thesis also intends to use the data and apply machine learning algorithms for automatic classifications of sentiment scores on twitter.
The results of the thesis show that most tweets have a higher positive sentiment scores compare to negative sentiment scores and that it is able to use machine learning algorithms to automatically analysis social data and classify the data. This thesis contributes to the understanding of how people perceive vaccine risk by providing big data analysis on a widely used social media platform via twitter. The results provide insight on how to better understand people’s sentiment on the topic of vaccine on twitter. | |