ANALISIS SENTIMEN TERHADAP ULASAN APLIKASI PEJABAT PENGELOLA INFORMASI DAN DOKUMENTASI KEMENTERIAN DALAM NEGERI REPUBLIK INDONESIA DI GOOGLE PLAYSTORE MENGGUNAKAN METODE SUPPORT VECTOR MACHINE
The Information and Documentation Management Officer (PPID) application was built as an application to meet the needs of information management and services by Public Bodies for the implementation of Law No. 14 of 2008 about Public Information Disclosure (UU KIP). This application assists public bodies in documenting and serving requests for information to the public. With the launch of the PPIPD application on the Google Play Store, it raises many opinions or responses from application users through the review feature. The reviews are quite many and unstructured and contain opinions from users about their satisfaction with the application. The feedback obtained from users is not only positive but also negative. Users often make complaints about applications that have been used or provide suggestions for features in the application. User reviews are of great interest to the owners of the application to decide the future. Sentiment analysis is an activity used to analyze a person's opinion or opinion on a topic. The Support Vector Machine (SVM) method is a text mining method that includes a classification method and the term Frequency-Inverse Document Frequency (TF-IDF) is a character weighting method. SVM and TF-IDF can be used to analyze sentiment based on user reviews of PPID apps on the Google Play Store. The purpose of this study was to classify user reviews of PPID apps on the Google Play Store using sentiment analysis that has been collected and filtered. The reviews totaled 700 data with labels of 85 positive and 615 negative. And the results of the analysis using SVM produced an average k-fold of 88%, precision of 94%, recall of 100%, f-measure of 97%, and accuracy of 97%.
Keywords: PPID; Sentiment Analysis, Support Vector Machine, TF-IDF
B. Zhao, "Web Scraping," in Springer International Publishing AG, USA, 2017.
Caughlin, D. E. (2017). An Introduction to Human Resource Analytics Using R . Version 0.1.1: 2022-05-18.
Karthick, R. & Malathi, D.A., 2015. Preprocessing of Various Data Sets Using Different Classification Algorithms for Evolutionary Programming. International Journal of Science and Research (IJSR), IV(4), pp.2730-33.
Lidya, S.K., Sitompul, O.S. & Efendi, S. (2015). Sentiment Analysis Pada Teks Bahasa Indonesia Menggunakan Support Vector Machine (SVM) dan K-Nearest Neighbor (K- NN). Seminar Nasional Teknologi Informasi dan Komunikasi.
Nurhayati., Iwan K, Hadihardaja., Indratmo Soekarno., & M. Cahyono. 2014. A Study of Hold-Out and K-Fold Cross Validation for Accuracy of Groundwater Modeling in Tidal Lowland Reclamation Using Extreme Learning Machine. 2nd International Conference on Technology, Informatics, Management, Engineering & Environment. pp : 228 – 233.
Patel, S. (2017, Mei 3). Chapter 2 : SVM (Support Vector Machine)—Theory. Dipetik April 11, 2018, dari Machine Learning 101:https://medium.com/machine-learning-101/chapter-2-svm-support-vector-machine-theory-f0812effc72.
Putranti, N. D. & Winarko, E., 2014. Analisis Sentimen Twitter untuk Teks Berbahasa Indonesia dengan Maximum Entropy dan Support Vector Machine. IJCCS, Volume 8, pp. 91-100.
Ramos, S., Soares, J., Cembranel, S. S., Tavares, I., Foroozandeh, Z., Vale, Z., & Fernandes, R. (2021). Data mining techniques for electricity customer characterization. Procedia Computer Science, 186, 475 – 488. https://doi.org/10.1016/j.procs.2021.04.168.
Rizki, M., Umam, M. I. H., & Hamzah, M. L. (2020). Aplikasi Data Mining Dengan Metode CHAID Dalam Menentukan Status Kredit. SITEKIN: Jurnal Sains, Teknologi dan Industri, 18 (1), 29 - 33.
Salekhah, C.I. (2016). Implementasi Metode Multi Class Support Vector Machine Untuk Klasifikasi Emosi pada Lirik Lagu Bahasa Indonesia. Universitas Komputer Indonesia (Unikom).