Study of Food Tech Recognition using Text Mining and Sentiment Analysis

As food tech has become a core industry not only in the restaurant industry but also in various other industries, this study was conducted to extract meaningful patterns and insights based on ‘food tech’ data. In addition, emotional analysis was used to identify consumers' hidden emotional perceptions, providing important insights for the development of the food tech industry. Next, CONCOR analysis and sentiment analysis were conducted to identify the connection between related words. Analysis tools were visualized using Textome and UCINET 6.0 programs. The research results are as follows. First, four clusters were extracted based on the frequency of the top 60 words and TF-IDF analysis among the 7,028 related words extracted with the 'Food Tech' keyword, 'Innovation & Future', 'Process & Effort', and 'Skill and business’ and ‘Etc’. Sentiment analysis shown that 1,303 out of a total of 1,816 documents were classified as positive documents (71%), 403 were classified as neutral, and 110 documents were classified as negative. Additionally, current study could confirm negative perceptions related to policy support and reactions to digital underdogs. Based on these research results, this study proposed meaningful implications for related industries by increasing operational efficiency related to food tech and creating new business opportunities. Furthermore, present study verified that we need to consider specific and step-by-step policies related to food tech and the technical aspect as an abbreviation.