Analisa Sentimen Financial Technology Peer To Peer Lending Pada Aplikasi Koinworks

  1. Beranda
  2. Vol 9, No 6
  3. Rousyati

Penulis

Rousyati Rousyati, Windu Gata, Dany Pratmanto, Nia Kusuma Wardhani

Abstrak

Bertambahnya jumlah perusahaan financial technology (fintech) yang terdaftar di Otoritas Jasa Keuangan mengartikan bahwa industri ini semakin dilirik karena  dibutuhkan dalam sistem perekonomian di Indonesia. Namun perkembangan Fintech P2PL telah menimbulkan beberapa risiko. Pertama, ada risiko gagal bayar, karena tidak ada jaminan atau persyaratan kontak fisik. Kedua, ada risiko yang terkait dengan keamanan data (risiko cyber), tata kelola, dan privasi pelanggan dan juga karena kerentanan sistem dan penyalahgunaan data, baik sengaja atau tidak sengaja. Ulasan yang terdapat pada kolom komentar Google Play dapat dimanfaatkan sebagai sumber data yang dapat di oleh dengan data mining. Penelitian ini akan menganalisis mengenai permasalahan yang berkaitan dengan beberapa ulasan tentang  Fintech P2PL  apikasi Koinworks pada ulasan di Google Play Store serta menentukan hasil akurasi analisis sentimen yang dihasilkan algoritma Decision Tree, K-Nearest Neigbor dan Support Vector Machine. Adapun manfaat dari penelitian ini adalah untuk membantu manajemen aplikasi Koinworks mengenai opini positif atau negatif dari pengguna aplikasi serta dapat  memberikan bukti  secara  empiris  untuk  teori  yang  berkaitan sehingga  dapat  dijadikan  sumbangan  pemikiran untuk pengembangan teori berikutnya. Algoritma SVM dengan Cross Validation + Parameter Optimization menghasilkan Accuracy 91,03% precision tertinggi yaitu dengan 96,73%% , recall 85,34% dan AUC  tertinggi yaitu 0,986 yang termasuk dalam excellent classification.

 

Abstract

The increasing number of financial technology (fintech) companies registered with the Financial Services Authority means that this industry is increasingly being looked at because it is needed in the economic system in Indonesia. However, the development of Fintech P2PL has created several risks. First, there is a risk of default, because there are no guarantees or physical contact requirements. Second, there are risks associated with data security (cyber risk), governance, and customer privacy and also because of system vulnerabilities and data abuse, whether intentionally or unintentionally. Reviews contained in the Google Play comments column can be used as a data source that can be shared with data mining. This research will analyze the problems related to some reviews about the Fintech P2PL Koinworks application on reviews on the Google Play Store and determine the results of the accuracy of sentiment analysis produced by the Decision Tree algorithm, K-Nearest Neigbor and Support Vector Machine. The benefits of this research are to help the management of Koinworks applications regarding positive or negative opinions of application users and can provide empirical evidence for related theories so that they can be contributed to the development of subsequent theories. SVM algorithm with Cross Validation + Parameter Optimization produces Accuracy 91.03% of the highest precision with 96.73 %%, 85.34% recall and the highest AUC of 0.986 which is included in excellent classification.


Teks Lengkap:

PDF

Referensi


AAPUTRA, S.A., DIDI ROSIYADI, WINDU GATA AND SYEPRY MAULANA HUSAIN, 2019. Sentiment Analysis Analisis Sentimen E-Wallet Pada Google Play Menggunakan Algoritma Naive Bayes Berbasis Particle Swarm Optimization. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 3(3), pp.377–382.

AJI, S., WARJIYONO, W., PRATMANTO, D., ARDIANSYAH, A., WIDODO, A., FAQIH, H., SULEMAN, S. AND FANDHILAH, F., 2019. Review Sentiment Analysis of World Class Hotel Using Naive Bayes Classifier And Particle Swarm Optimization Method. [online] (January 2018). Available at: .

BALAKRISHNAN, V., SELVANAYAGAM, P.K. AND YIN, L.P., 2020. Sentiment and Emotion Analyses for Malaysian Mobile Digital Payment Applications. [online] pp.67–71. Available at: .

CHANGE.ORG, 2018. Penagihan Pinjaman Fintech Sangat Meresahkan. [online] Available at: .

IGNATOW, G. AND MIHALCEA, R., 2015. An introduction to text mining. Research Design, Data Collection, and Analysis.

JIANG, C., WANG, Z., WANG, R. AND DING, Y., 2018. Loan default prediction by combining soft information extracted from descriptive text in online peer-to-peer lending. Annals of Operations Research, 266(1–2), pp.511–529.

KURNIAWAN, T.A., WARDANI, D.K. AND WIDHAYATI, L., 2019. Pengaruh Keberterimaan Layanan Peer To Peer Lending Kepada Umkm Sebagai Pengguna Dengan Menggunakan Metode Technology Acceptance Model (Tam). Jurnal Sosial Ekonomi Dan Humaniora, [online] 5(2), pp.151–160. Available at: .

MAHENDRAJAYA, R., BUNTORO, G.A. AND SETYAWAN, M.B., 2019. Analisis Sentimen Pengguna Gopay Menggunakan Metode Lexicon Based Dan Support Vector Machine. Komputek, [online] 3(2), p.52. Available at: .

NARAIN, A., 2017. Two Faces of Change. Finance & Development.

NUGRAHA, A.P., ROLANDO, PUSPASARI, M.A. AND SYAIFULLAH, D.H., 2019. Usability Evaluation for User Interface Redesign of Financial Technology Application. IOP Conference Series: Materials Science and Engineering, [online] 505(1). Available at: .

OJK, 2020. Perkembangan Fintech Lending. [online] Available at: .

PRANATA, N. AND FARANDY, A.R., 2019. Big Data-Based Peer-to-Peer Lending Fintech: Surveillance System through Utilization of Google Play Review. SSRN Electronic Journal, (943).

PRIHONO, O.F. AND SARI, P.K., 2019. Comparison Analysis Of Social Influence Marketing For Mobile Payment Using Support Vector Machine. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, [online] 4(4), pp.367–374. Available at: .

PRIYADHARSINI.C AND THANAMANI, D.A.S., 2014. An Overview of Knowledge Discovery Databaseand Data mining Techniques. International Journal of Innovative Research in Computer and Communication Engineering, [online] 2(1), pp.1571–1578. Available at: .

RAMADHANI, N., 2019. 10 Platform P2P Lending Terbaik Versi KPMG di Fintech Edge. [online] www.akseleran.co.id. Available at: .

SUDIRA, H., DIAR, A.L. AND RULDEVIYANI, Y., 2019. Instagram Sentiment Analysis with Naive Bayes and KNN: Exploring Customer Satisfaction of Digital Payment Services in Indonesia. 2019 International Workshop on Big Data and Information Security, IWBIS 2019, [online] pp.21–26. Available at: .

SUROHMAN, AJI, S., ROUSYATI AND WATI, F.F., 2020. Analisa Sentimen Terhadap Review Fintech Dengan Metode Naive Bayes. Evolusi: Jurnal Sains dan Manajemen, [online] 8(1), pp.93–105. Available at: .

WISNU, H., AFIF, M. AND RULDEVYANI, Y., 2020. Sentiment analysis on customer satisfaction of digital payment in Indonesia: A comparative study using KNN and Naïve Bayes. Journal of Physics: Conference Series, [online] 1444(1). Available at: .

WULANDARI, P.P., 2017. Analisis Faktor-Faktor Yang Menentukan Keputusan Pemberian Kredit Untuk Usaha Mikro, Kecil, Dan Menengah (Umkm) Pada Lembaga Pembiayaan Peer To Peer Lending. Journal of Chemical Information and Modeling, [online] 53(9), pp.1689–1699. Available at: .




DOI: http://dx.doi.org/10.25126/jtiik.2022964409

Refbacks

  • Saat ini tidak ada refbacks.