Analyzing customer and student feedback collected during a social experiment on nutrition and dietetics among students.
Text
Question AnsweringThe project focused on analyzing customer and student feedback collected during a social experiment on nutrition and dietetics among students. The main objective was to help researchers and AI systems better understand students’ eating habits, dietary preferences, health awareness, and reactions to different nutrition programs and recommendations. My role involved data labeling and annotation of textual feedback gathered through surveys, questionnaires, and online responses. Specific tasks included sentiment analysis labeling (positive, negative, and neutral responses), text classification, keyword tagging, and categorizing feedback into themes such as healthy eating habits, food affordability, dietary challenges, meal preferences, and awareness of nutrition-related issues. The project involved reviewing and labeling large volumes of unstructured text data while following strict annotation guidelines to ensure consistency and accuracy. The dataset consisted of several thousand student feedback entries collected across different institutions and demographic groups. Performance was measured using annotation accuracy, consistency scores, turnaround time, and quality review feedback from project supervisors. This project strengthened my attention to detail, analytical thinking, and ability to manage high-volume data labeling tasks efficiently while maintaining quality standards.