<![CDATA[The increasing integration of digital services in Indonesia has driven the development of the Digital Population Identity (IKD) application, aimed at enhancing citizen access to demographic data and optimizing administrative processes. This study explores public sentiment toward the IKD by analyzing 20,703 user reviews from the Google Play Store. Reviews were preprocessed using case folding, normalization, stopword removal, tokenization, and stemming, then transformed into numerical features using the Term Frequency-Inverse Document Frequency (TF-IDF) technique. Sentiment categories positive, neutral, and negative were determined based on user rating scores. Two machine learning algorithms, Support Vector Machine (SVM) and Decision Tree, were utilized due to their respective strengths: SVM for its effectiveness in handling high-dimensional text data and Decision Tree for its interpretability, which is relevant for public sector applications. Evaluation results indicate that the SVM model achieved an accuracy of 85.46%, while the Decision Tree attained 80.68%. Both models showed strong performance in detecting positive and negative sentiments, yet encountered challenges in classifying neutral sentiments due to data imbalance. These results demonstrate the potential of sentiment analysis as a practical approach for assessing public perception of digital government applications. The insights gained may support policymakers and developers in identifying service gaps, enhancing user experience, and formulating data-driven strategies to improve the delivery of digital public services in Indonesia.]]>
Copyrights © 2025
