텍스트 마이닝을 활용한 감귤껍질 연구 동향 분석

Abstract

This study focuses on the creation of the tangerine peel industry through text mining for domestic studies. In an era when big data analysis is essential, various analysis tools and programming languages have emerged, among which Python is the most preferred language for algorithm generation and is used for data analysis. In addition, tangerine peel sold on the market has various effects, so it is deeply related to health. However, the burden of eating tangerine peel and consumers' interest are low. To solve this problem, it is necessary to analyze text mining for tangerine peel and check keywords related to tangerine peel. The purpose of this study was to conduct text mining through Python, which is used for data analysis. In addition, the differences were compared by dividing the quarter every 10 years from 1990 to 2022. It can be predicted that it will be used as a health functional food for tangerine peel. In this study, text mining was conducted focusing on 108 papers provided by RISS. This study was conducted focusing on domestic academic research and domestic degree papers, and it was confirmed that extraction and content were the keywords with the highest frequency of appearance. In addition, with the emergence of new keywords such as paint and coal, it can be seen that various studies are being conducted, and studies related to tangerine peel have continued to increase. Finally, in this paper, text mining was conducted through Python, and it was found that it was possible to modify through Python if additional analysis as well as existing keyword frequency analysis and word cloud were required. This study can be a useful reference for the industrialization strategy of Jeju tangerine peel.