Development of a Model and Algorithm for Data Aggregation and Classification for a Personalized Nutrition Recommendation System

The article demonstrates the design and implementation of a data aggregation algorithm for a future recommendation system in the field of personalized nutrition. It was based on theoretical materials on machine learning methods in natural language processing, as well as tutorials on building classification models using the Keras library. A distinctive feature of the classifier implemented within the framework of this project is the fact that it simultaneously accepts images and text data as input to obtain more accurate and balanced predictions. The implementation of the designed data aggregation algorithm for the recommendation system in the field of personalized nutrition is considered in detail. A review was made of the tools and approaches chosen at various stages of aggregation. The metrics for evaluating the predictions of the implemented model for the classification of geographic labels, as well as the analysis of the average sentiment of user reviews are determined and the results are visualized. Predicted geo tags and revealed comment sentiments were added to the main data frame as additional features.