빅데이터를 활용한 식품 유통 플랫폼에 대한 소비자 인식 분석: 텍스트 마이닝과 의미연결망 분석을 중심으로

Fresh-food delivery platform service has shown significant growth due to the increase in sin- gle-person households and working women, and the increase in untact consumption caused by the COVID-19 pandemic. Therefore, this study aims to explore the consumers’ perception of the fresh-food delivery platform service using big data. In order to analyze big data, ‘fresh-food delivery platform service’ related documents that had been generated from January 1, 2015 to August 31, 2020 were collected from major portal sites (“Naver” and “Daum”) using Textom. A total of 58,939 documents were collected. Non-relevant and in- accurate words were removed for text mining. Top 90 keywords, such as “fresh-food”, “product”, “shipping”, “purchase”, “home”, “COVID-19”, “increase”, and “price”, were extracted through the frequency analysis and TF-IDF(Term Frequency - Inverse Document Frequency) analysis. Through semantic network analysis using UCINET6.0 and Netdraw, it was found that “fresh-food”, “product”, “shipping”, and “purchase” were highly interrelated with other keywords. Through CONCOR (Convergence of iteration Correlation) analysis, keywords were classified into seven clusters, such as “food purchasing trends”, “food delivery platform at- tributes”, “Rocket Fresh service”, “delivery service”, “specialized food shopping channel”, “HMR(home meal replacement)”, and “fresh-food products”. Based on these results, consumers’ perceptions and issues of fresh-food delivery were identified. Moreover, this study will provide not only theoretical implications for future research but also practical implications for developing successful marketing strategies.