Date Thesis Awarded

4-2021

Access Type

Honors Thesis -- Open Access

Degree Name

Bachelors of Science (BS)

Department

Mathematics

Advisor

Anh Ninh

Committee Members

Heather Sasinowska

Tyler Davis

Abstract

Blockchain as a technology has brought with it a wave of promises and expectations. After its successes in the financial sector, many potential new applications of the technology have been theorized across a variety of sectors. Blockchain’s application to healthcare stands out among these theories. Healthcare is a sector that views technological innovation under more scrutiny, so the introduction of blockchain into healthcare is a particularly unique implementation of the technology. Attempting to understand how blockchain is accepted in the healthcare industry is a difficult problem due to the nature of data associated with the sector. One avenue to understand how blockchain is viewed by this sector is through analysis of social media micro-blogging on the Twitter platform. By archiving a time series of tweets, important questions about how blockchain is viewed in healthcare can be addressed with the natural language processing technique of sentiment analysis. An ensemble of BERT models are identified as the best classifier with the given training data, and are further applied to a time series of tweets about blockchain in healthcare. This study analyzes healthcare perceptions of blockchain based on these results, and finds that the distribution of sentiment is largely positive. Examining the volume of tweets over time also indicates a massive increase in interest in the topic in 2018. Finally, when exploring how company accounts tweet compared to personal accounts, it is found that personal accounts produce slightly more positive tweets relative to company accounts. Thus, it is understood that healthcare perception of blockchain became consistently positive following 2017.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 License.

Download

Share Feedback

Share

COinS