K-NN Method for Review Analys Product Accounting Software
Many companies have not implemented accounting software in financial management. Even though the current era of technology is increasingly updated and developing, more and more superior products are being issued by software development companies, especially in accounting software. There are not a few software products whose quality is still below standard or incomplete with features and facilities. So that researchers concentrate on companies or individual businesses that still use manual methods in processing their finances by helping and making it easier to choose the software product they will choose. Researchers first carry out the accounting software product selection stage based on an opinion or opinion of the public who have bought and used the software they choose and they pour this opinion into online media such as comments on a product selling site. Thousands of comments will be processed and grouped into data sets and this time the researcher processes the data classification using the k-Nearest Neighbor (K-NN) algorithm. By using the K-NN method, it is expected to be able to produce the expected accuracy value so that the data set processing is stronger and more valid. It turns out that after applying the data accuracy value obtained by 80.50%, it can be concluded that the K-NN method is very suitable for the concept of text mining this time and for selecting the data set in the form of text.
Y. Yin, D. Han, and Z. Cai, “Explore Data Classification Algorithm Based on SVM and PSO for Education Decision,” J. Converg. Inf. Technol., 2011, doi: 10.4156/jcit.vol6.issue10.16.
F. Gorunescu, Data Mining: Concepts and Techniques. 2011.
P. Kasih, “Perlindungan Hukum Bagi Masyarakat Terhadap Peredaran Barang Palsu,” J. Univ. Atma Jaya Yogyakarta, vol. 5, no. 6, pp. 12–21, 2016.
M. Berndtsson, J. Hansson, B. Olsson, and B. Lundell, Thesis Guide - A Guide for Students in Computer Science and Information Systems. 2010.
D. P. Langgeni, Z. K. A. Baizal, and Y. F. A. W, “Clustering Artikel Berita Berbahasa Indonesia,” Semin. Nas. Inform., 2010.
M. Abdous, W. He, and C. J. Yen, “Using Data Mining for Predicting Relationships Between Online Question Theme and Final Grade,” Educ. Technol. Soc., vol. 15, no. 3, pp. 77–88, 2012.
M. S. Hudin, M. A. Fauzi, and S. Adinugroho, “Implementasi Metode Text Mining dan K-Means Clustering untuk Pengelompokan Dokumen Skripsi (Studi Kasus: Universitas Brawijaya),” J. Pengemb. Teknlogi Inf. dan Ilmu Komput., vol. 2, no. 11, pp. 5518–5524, 2018.
Copyright (c) 2020 Jurnal Ilmiah Informatika
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.