<![CDATA[The rapid growth of digital platforms has encouraged customers to share their experiences and evaluations through online reviews, particularly on Google Maps. These reviews provide valuable insights that can support Customer Relationship Management (CRM) strategies when analyzed systematically. This study aims to analyze customer review sentiment toward Coffee Shop Z in Purwokerto using the Multinomial Naïve Bayes algorithm and to utilize the findings as a basis for CRM strategy formulation through the get, keep, and grow framework. A mixed-method approach was employed, combining quantitative sentiment analysis of 242 Google Maps reviews and qualitative interviews with customers for methodological triangulation. The research process included data collection through web scraping, text preprocessing, TF-IDF feature extraction, sentiment labeling, classification modeling, and performance evaluation. The results indicate that negative sentiment dominated customer reviews (57.02%), followed by neutral sentiment (30.16%) and positive sentiment (12.80%). The classification model achieved an accuracy of 63.27%, with stronger performance in identifying negative sentiment than neutral and positive sentiments. The findings reveal that customer dissatisfaction is primarily associated with service quality and waiting time, while positive perceptions are related to food quality, affordability, and cleanliness. Based on these findings, CRM strategies were developed through customer acquisition (get), retention (keep), and loyalty enhancement (grow) initiatives. This study demonstrates that sentiment analysis can serve not only as a customer perception measurement tool but also as a valuable source of evidence-based recommendations for customer relationship management and digital marketing strategy development.]]>
Copyrights © 2025
