Aspect-Based Sentiment Analysis of Global, National, and Local Coffee Consumer Perceptions on Google Reviews Using a Python Model

This study investigates consumer sentiments toward three tiers of coffee brands: global, national and local, using an aspect-based sentiment analysis (ABSA) of Google Maps Reviews. Data collection and analysis were conducted on a dataset of 3,034 reviews in Bahasa Indonesia from one brand for each tier. The research employed a nine-stage Python pipeline, starting from text preprocessing and followed by a rule-based approach for aspect extraction, followed by lexicon-based sentiment analysis, feature creation, model building and training with 5-fold stratified cross-validation. Five aspects were analyzed, as perceived by consumers:   ambiance, packaging, price, service and taste. The research examined and compared seven supervised machine learning classifiers, including IndoBERT, SVM, Random Forest, Naive Bayes, Logistic Regression, Gradient Boosting and Decision Tree, under identical conditions, evaluating each about its accuracy along with weighted and macro-averaged precision, recall and F1-score. IndoBERT achieved the highest outcome with 0.9275 accuracy and 0.9275 weighted F1 and 0.8449 macro F1 metrics, closely trailed by SVM with 0.9242 accuracy and 0.9229 weighted F1. Cross-tier analysis revealed generally positive sentiments toward all three categories of coffee brands. Global brands were favored for their ambiance and taste but criticized for price and inconsistent service. National brands also had positive sentiments for ambiance and taste, yet there were observations of inconsistencies among outlets and long wait times for customers. Local brands were positively associated with their ambiance and taste but had some drawbacks, such as limited seating due to operational constraints. These findings may contribute to the development of more effective e-business strategies, improved customer relationship management and the designing of digital customer experiences within the Indonesian coffee retail landscape.