Sentiment Analysis of BNI Mobile Application Using The K-Nearest Neighbor Algorithm (KNN) With Particle Swarm Optimization (PSO) Feature Selection

  • Dewi Yustika Lakoro Universitas Amikom Yogyakarta
  • Ema Utami Universitas Amikom Yogyakarta
  • Dhani Ariatmanto Universitas Amikom Yogyakarta


Analysis sentiment is field studies analyze opinions, sentiments, evaluations, attitudes and emotions to entity like products, services, organizations, individuals, issues, events, films and topics. Sentiment analysis first succeed used previously in various fields, such as movie ratings, service ratings, product ratings, etc. and recently This get popularity in the field economy especially on e- commerce applications. Moment This industry banking do various innovation finance that is shift their focus from banking traditional to banking based technology for fulfil need customers as well as For increase Power competitive. Mobile banking is one of them from innovation that. Response in use of this mobile banking application enter every the day with amount response as much hundreds so that response the difficult For sorted become responses included positive or including negative response. Study This using private data which is comment BNI Mobile banking application in the application laystore. Existing data Then will be done preprocessing with do a number of stages, ie started from tokenization, stemming, stopword removal and Term Frequency Inverse Document Frequency (TF-IDF) was carried out. Initial process carried out in classification is accept input comment data then the preprocessing process is carried out, then included in the classification model, method classification used is K-Nearest Neighbor with particle swarm optimization Optimization and finally is the results issued is accuracy from method used. After That researcher do optimization use one algorithm optimization namely PSO with combine with KNN or called KNN-PSO gain accuracy of 92.33% or only has an error of 7.67%. If seen from the amount of data is successful do classification as many as 277 data, in meaning only has 23 errors or missing data succeed classified with good.


Ainurrohma. (2021). Akurasi Algoritma Klasifikasi pada Software Rapidminer dan Weka. PRISMA, Prosiding Seminar Nasional Matematika, 4, 493–499.
Idrus, Ali, Herlambang Brawijaya, and Maruloh. (2018). Sentiment Analysis Of State Officials News On Online Media Based On Public Opinion Using Naive Bayes Classifier Algorithm And Particle Swarm Optimization. In 2018 6th International Conference on Cyber and IT Service Management (CITSM), 1–7. Parapat, Indonesia: IEEE.
Ismail, Abdul Rahman, Ahmad Zainul Fanani, Guruh Fajar Shidik, and Muljono. (2020). Implementation Of Naive Bayes Algorithm With Particle Swarm Optimization In Classification Of Dress Recommendation. In 2020 International Seminar on Application for Technology of Information and Communication (ISemantic), 174–78. Semarang, Indonesia: IEEE.
Nursiah, N., Ferils, M., & Kamarudin, J. (2022). Analisis minat menggunakan mobile banking. Akuntabel, 19(1), 91–100.
Ridwansyah, T. (2022). Implementasi Text Mining Terhadap Analisis Sentimen Masyarakat Dunia Di Twitter Terhadap Kota Medan Menggunakan K-Fold Cross Validation Dan Naïve Bayes Classifier. KLIK: Kajian Ilmiah Informatika Dan Komputer, 2(5), 178–185.
Sharma, Ankita, and Udayan Ghose. (2020). Sentimental Analysis of Twitter Data with Respect to General Elections in India. Procedia Computer Science 173: 325–34.
Pajri, D., Umaidah, Y., & Padilah, T. N. (2020). K-Nearest Neighbor Berbasis Particle Swarm Optimization untuk Analisis Sentimen Terhadap Tokopedia. Jurnal Teknik Informatika Dan Sistem Informasi, 6(2).
Widya Sihwi, Sari, Insan Prasetya Jati, and Rini Anggrainingsih. (2018). Twitter Sentiment Analysis of Movie Reviews Using Information Gain and Naïve Bayes Classifier. In 2018 International Seminar on Application for Technology of Information and Communication, 190–95. Semarang: IEEE.
Abstract viewed = 5 times
PDF downloaded = 6 times