The rapid growth of the café industry in Kudus has given residents plenty of options for places to hang out. Customer reviews on Google Maps serve as a vital information source, as they contain customer opinions and satisfaction levels regarding a particular cafe. However, the sheer volume of review data makes manual analysis less effective. This study aims to analyze the sentiment of Google Maps reviews for 10 cafés in Kudus (2023–2025) using the TF-IDF method and a Logistic Regression algorithm based on K-Fold Cross-Validation. Research data was obtained through web scraping, comprising 3,393 Google Maps reviews. The research stages included data preprocessing (text normalization, tokenization, stopword removal), feature extraction using TF-IDF, splitting the data into 80% training and 20% testing sets, training the Logistic Regression model, and evaluating model performance using K-Fold Cross-Validation. The experimental results show that the TF-IDF-based Logistic Regression model is capable of classifying positive and negative reviews well, yielding an accuracy of approximately 86,68%, precision of 92,45%, recall of 91,71%, and an F1-score of 92,08%. This study is expected to help the public determine recommendations for the best coffee shops in Kudus based on objective customer opinions, as well as serve as a reference for business owners to improve service quality and customer satisfaction.
Copyrights © 2026