Pertumbuhan pesat layanan fintech di Indonesia mendorong perlunya evaluasi kualitas layanan yang objektif dan berbasis data. Penelitian ini bertujuan untuk mengevaluasi persepsi pengguna terhadap layanan ShopeePay dengan menggunakan pendekatan analisis sentimen berbasis algoritma Support Vector Machine (SVM). Data ulasan pengguna dikumpulkan dari platform digital dan melalui tahapan pra-pemrosesan teks serta ekstraksi fitur menggunakan metode Term Frequency–Inverse Document Frequency (TF–IDF). Dataset dibagi menjadi data latih (80%) dan data uji (20%) untuk membangun serta mengevaluasi model klasifikasi. Hasil pengujian menunjukkan bahwa model SVM mampu mengklasifikasikan sentimen pengguna dengan baik, dengan akurasi mencapai 84% dan F1-score tertinggi pada kategori sentimen positif. Analisis kata dominan mengungkap bahwa sentimen positif didominasi oleh kata seperti “mudah” dan “cepat”, sedangkan sentimen negatif terkait dengan “error” dan “saldo hilang”. Meskipun demikian, analisis kesalahan menunjukkan bahwa model masih menghadapi tantangan dalam menangani ulasan dengan unsur sarkasme, kritik implisit, dan opini campuran, yang dapat memengaruhi ketepatan klasifikasi. Secara praktis, hasil penelitian ini memberikan wawasan strategis bagi pengembang ShopeePay dalam meningkatkan kualitas layanan, terutama melalui optimalisasi fitur transaksi dan penanganan kendala teknis yang sering dikeluhkan pengguna. Dengan demikian, pendekatan analisis sentimen berbasis machine learning ini dapat menjadi alat evaluasi yang efektif untuk meningkatkan pengalaman pengguna dan daya saing layanan fintech di Indonesia. Abstract The rapid growth of fintech services in Indonesia underscores the need for an objective and data-driven evaluation of service quality. This study aims to assess user perceptions of the ShopeePay service using a sentiment analysis approach based on the Support Vector Machine (SVM) algorithm. User review data were collected from digital platforms and underwent text preprocessing and feature extraction using the Term Frequency–Inverse Document Frequency (TF–IDF) method. The dataset was divided into training (80%) and testing (20%) subsets to build and evaluate the classification model. Experimental results indicate that the SVM model effectively classifies user sentiments, achieving an accuracy of 84% and the highest F1-score in the positive sentiment category. Dominant word analysis revealed that positive sentiments were associated with words such as “easy” and “fast,” while negative sentiments were related to “error” and “lost balance.” However, the error analysis showed that the model still faces challenges in handling reviews containing sarcasm, implicit criticism, and mixed opinions, which can affect classification accuracy. From a practical perspective, the findings provide strategic insights for ShopeePay developers to enhance service quality—particularly by optimizing transaction features and addressing common technical issues reported by users. Consequently, this machine learning-based sentiment analysis approach serves as an effective evaluation tool for improving user experience and strengthening the competitiveness of fintech services in Indonesia.
English
Pertumbuhan pesat layanan fintech di Indonesia mendorong perlunya evaluasi kualitas layanan yang objektif dan berbasis data. Penelitian ini bertujuan untuk mengevaluasi persepsi pengguna terhadap layanan ShopeePay dengan menggunakan pendekatan analisis sentimen berbasis algoritma Support Vector Machine (SVM). Data ulasan pengguna dikumpulkan dari platform digital dan melalui tahapan pra-pemrosesan teks serta ekstraksi fitur menggunakan metode Term Frequency–Inverse Document Frequency (TF–IDF). Dataset dibagi menjadi data latih (80%) dan data uji (20%) untuk membangun serta mengevaluasi model klasifikasi. Hasil pengujian menunjukkan bahwa model SVM mampu mengklasifikasikan sentimen pengguna dengan baik, dengan akurasi mencapai 84% dan F1-score tertinggi pada kategori sentimen positif. Analisis kata dominan mengungkap bahwa sentimen positif didominasi oleh kata seperti “mudah” dan “cepat”, sedangkan sentimen negatif terkait dengan “error” dan “saldo hilang”. Meskipun demikian, analisis kesalahan menunjukkan bahwa model masih menghadapi tantangan dalam menangani ulasan dengan unsur sarkasme, kritik implisit, dan opini campuran, yang dapat memengaruhi ketepatan klasifikasi. Secara praktis, hasil penelitian ini memberikan wawasan strategis bagi pengembang ShopeePay dalam meningkatkan kualitas layanan, terutama melalui optimalisasi fitur transaksi dan penanganan kendala teknis yang sering dikeluhkan pengguna. Dengan demikian, pendekatan analisis sentimen berbasis machine learning ini dapat menjadi alat evaluasi yang efektif untuk meningkatkan pengalaman pengguna dan daya saing layanan fintech di Indonesia. Abstract The rapid growth of fintech services in Indonesia underscores the need for an objective and data-driven evaluation of service quality. This study aims to assess user perceptions of the ShopeePay service using a sentiment analysis approach based on the Support Vector Machine (SVM) algorithm. User review data were collected from digital platforms and underwent text preprocessing and feature extraction using the Term Frequency–Inverse Document Frequency (TF–IDF) method. The dataset was divided into training (80%) and testing (20%) subsets to build and evaluate the classification model. Experimental results indicate that the SVM model effectively classifies user sentiments, achieving an accuracy of 84% and the highest F1-score in the positive sentiment category. Dominant word analysis revealed that positive sentiments were associated with words such as “easy” and “fast,” while negative sentiments were related to “error” and “lost balance.” However, the error analysis showed that the model still faces challenges in handling reviews containing sarcasm, implicit criticism, and mixed opinions, which can affect classification accuracy. From a practical perspective, the findings provide strategic insights for ShopeePay developers to enhance service quality—particularly by optimizing transaction features and addressing common technical issues reported by users. Consequently, this machine learning-based sentiment analysis approach serves as an effective evaluation tool for improving user experience and strengthening the competitiveness of fintech services in Indonesia.
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.