DESIGN AND IMPLEMENTATION OF AN ONLINE REVIEW ANALYTICS SOLUTION FOR QUICK-SERVICE RESTAURANTS

In the quick-service restaurant (QSR) industry, customer satisfaction is crucial for retaining current customers and attracting new ones. The growing use of digital platforms has fundamentally reshaped the way consumers share and access information; electronic word-of-mouth, especially in the form of online reviews, has become one of the most influential factors in diners’ restaurant selection. Reviews are an invaluable source of information not only for potential customers but also for businesses, as they provide direct insight into customer satisfaction and performance gaps. Building on prior research that identifies food quality, service quality, physical environment, and price as the primary drivers of customer satisfaction, this thesis proposes the design and implementation of an analytics solution that transforms unstructured online reviews into operational intelligence for QSRs. Developed in Keboola, the automated data pipeline collects publicly available reviews from Google Maps and Yelp and analyzes them to uncover sentiment trends and recurring themes. The results are visualized in an interactive Streamlit dashboard that enables managers to benchmark performance across locations and identify areas for improvement.