Analyzing Customer Preferences in Food Companies and Food Technology with Artificial Intelligence

The relationship between AI and consumer preferences is becoming a crucial area of study for both technology corporations and food industries in an increasingly digitalized environment. With the introduction of AI technologies, businesses can now monitor consumer behavior in novel ways and customize their products to appeal to their customers more intimately. The study of natural language processing aims to understand a language and enable machines to do meaningful tasks. This study emphasizes the use of sentiment analysis to improve service quality and gain a deeper understanding of costumer feedbacks. To find the favorable, negative, and neutral reviews about the policies the restaurant follows or violates, a real-time dataset was used. Following preprocessing, lexicon-based sentiment analyzers Textblob and Vader (valence aware dictionary for sentiment reasoning) are used to appropriately classify comments as either positive or negative. Oversampling is used to balance the data sets because there are more positive-labeled evaluations than negative ones. Training and test data for the feature extraction process are created using the count vectorizer and TF-IDF (Term Frequency Inverse Document Frequency). The results indicate that ease of use, product quality, and service effectiveness are strongly correlated with customer satisfaction. Businesses that put these factors first typically see an increase in client loyalty and favorable sentiment.