비정형 빅데이터 분석을 활용한 저가 커피전문점 트렌드 조사

A Study on the Trends of Low-cost Coffee Shop Using Unstructured Big Data Analysis

This study conducted big data analysis using text mining to identify trends and major issues of low-cost coffee shops during COVID-19. To this end, Textom, a textual data batch solution program, was used to derive keywords related to hotel packages through Naver, Google, Daum. The collection period was set from February 2020 to December 2022, when COVID-19 spread in earnest, a total of 18,429 keywords were derived, and the final 50 key keywords were used in the empirical analysis of this study through the purification process. First, as a result of frequency and TF-IDF analysis, the frequency was presented in the order of low price, price increase, brand, café start-up, mega coffee, TF-IDF value in the order of price increase, café start-up, mega coffee, brand, etc. Next, as a result of the centrality analysis, both degree centrality and eigenvector centrality were found in the following order: low price, price increase, brand, café start-up, mega coffee, franchise, and cost-effectiveness. Finally, CONCOR analysis, which rearranges and groups highly correlated words, was divided into five groups: brand, price, start-up, product, and marketing attributes of coffee. Through these analysis results, trends and major issues related to low-cost coffee shops were identified. It is also expected to present effective results for future research related to low-cost coffee shops and provide meaningful implications for implementing marketing strategies for competitive advantage.