Analyzing Digital Reputation and Business Sustainability of Restaurant in Makassar Based on Online Reviews Using K-Means Clustering

Abstract

This study explores the interplay between digital reputation and business sustainability among restaurants in Makassar, Indonesia, utilizing secondary data retrieved from TripAdvisor (n = 271). The dataset captures two principal facets of online reputation—customer ratings and review counts—which together reflect consumer perception and engagement within the digital marketplace. Clustering analysis was performed using the K-Means algorithm, an unsupervised learning method for partitioning data. To determine the optimal number of clusters, multiple evaluation metrics were applied, including the Elbow Method, Silhouette Score, Davies–Bouldin Index (DBI), and Calinski–Harabasz Index (CHI). Although k = 2 yielded the most statistically efficient configuration, a four-cluster model (k = 4) was chosen for its enhanced interpretability and managerial relevance. The four resulting segments—Star Performers, Hidden Gems, Mass Popular, and Low Performers—offer a nuanced representation of digital reputation strategies within Makassar’s culinary ecosystem. The findings reveal that highly rated restaurants with significant online engagement tend to exhibit stronger indicators of business resilience and customer trust. Beyond empirical segmentation, this study highlights the growing significance of digital ethics, data transparency, and responsible analytics as critical enablers of sustainable digital transformation. Overall, the research underscores the strategic role of data science in shaping ethical, inclusive, and sustainable business practices in the hospitality industry.