Article Per Year (5 Year)
p-Index From 2021 - 2026
1.857
P-Index
This Author published in this journals
All Journal Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Sinkron : Jurnal dan Penelitian Teknik Informatika Inform : Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi SPIRIT JATI (Jurnal Mahasiswa Teknik Informatika) Informatics, Electrical and Electronics Engineering Information Technology International Journal (ITIJ) INOVTEK Polbeng - Seri Informatika
Fitri Ana Wati, Seftin
Unknown Affiliation
Aerospace Engineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Library & Information Science

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
Sentiment Analysis E-Wallet Application Services Using the Support Vector Machine and Long Short-Term Memory Methods Arya Darmansyah, Mochammad Dzikri; Vitianingsih, Anik Vega; Lidya Maukar, Anastasia; Yuliani, SY.; Fitri Ana Wati, Seftin
INOVTEK Polbeng - Seri Informatika Vol. 11 No. 1 (2026): February
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/apedaz75

Abstract

The rapid growth of financial technology services in Indonesia has increased the volume of user reviews, yet their utilization for sentiment-based insights remains limited in the e-wallet sector. This study compares the effectiveness of Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) in classifying the sentiment of 3,185 DANA e-wallet reviews collected from the Google Play Store and Instagram. The research process includes text preprocessing, lexicon-based labeling, and feature extraction using TF-IDF for SVM and word embeddings for LSTM. Model evaluation is conducted using a confusion matrix based on accuracy, precision, and recall, without inferential statistical testing. The results show that LSTM outperforms SVM, achieving an accuracy of 86.66%, a recall of 81.86%, and a precision of 82.09%, while the best SVM variant with an RBF kernel attains an accuracy of 84.93%. This study contributes by identifying key service-related factors influencing user satisfaction and dissatisfaction and by providing practical, sentiment-based insights to support service quality improvement. The novelty lies in the multi-platform analysis of Indonesian e-wallet reviews and the direct comparison of classical machine learning and deep learning approaches without statistical hypothesis testing. These findings confirm the effectiveness of deep learning for sentiment analysis of unstructured Indonesian text.
Co-Authors Abdul Rezha Efrat Najaf Aminulloh Achri Biyanda, Margi Anik Vega Vitianingsih Apriyanti, Narti Arya Darmansyah, Mochammad Dzikri Ayu Pangestuti, Roro Aziiza, Arizia Aulia Cahyo Wibowo, Nur DWI CAHYONO Eka Damayanti, Natasya Fitri, Anindo Saka Ghibran Jhi S, Moch Lidya Maukar, Anastasia Lita Dwi Listyowati, Lita Dwi Ongko, Bagus Kustiono Pamudi Pamudi, Pamudi Permatasari, Reisa Pujiono, Halim Putra, Herlambang Haryo Rijaluddin, Khalid Riza , M. Syaiful Safitri, Eristya Maya Saka Fitri, Anindo Slamet Kacung, Slamet Suryo Widodo Vega Vitianingsih, Anik Wikanningrum , Anggit Yuliani, SY.