Analisis Ulasan Google Maps Wisata Bahari Lamongan Berbasis Servqual Menggunakan Algoritma Classifier Chains

Abstract

User reviews on Google Maps are a valuable source of information that can be utilized to evaluate the service quality of a tourist destination based on visitors' actual experiences. However, the sheer volume of reviews makes manual analysis highly inefficient. This study aims to analyze the sentiment of visitor reviews of Wisata Bahari Lamongan (WBL), classify these reviews into SERVQUAL service quality dimensions using the Classifier Chains algorithm, and provide recommendations for service improvement based on Importance Performance Analysis (IPA). The research data was obtained from WBL Google Maps reviews and processed through the Knowledge Discovery in Database (KDD) stages, which included data selection, preprocessing, sentiment analysis using the w11wo/indonesian-roberta-base-sentiment-classifier model, SERVQUAL dimension mapping, and multilabel classification using the Classifier Chains algorithm with several base classifiers. The test results indicate that the combination of Classifier Chains with Logistic Regression yielded the best performance compared to other models, achieving a Macro F1-Score of 0.4774 and a Weighted F1-Score of 0.6304. This combination proved highly capable of modeling the interdependencies between SERVQUAL dimensions. Furthermore, the classification results were utilized in IPA and Latent Dirichlet Allocation (LDA) to identify specific service attributes that need to be maintained or improved. This research demonstrates that integrating sentiment analysis, multilabel classification, SERVQUAL, and IPA can produce a more comprehensive evaluation of service quality based on online reviews. Ultimately, it provides strategic recommendations for the management of Wisata Bahari Lamongan to enhance service quality and boost visitor satisfaction.