Dampak positif yang ditimbulkan dari perkembangan teknologi salah satunya adalah kemudahan dalam menyampaikan aspirasi dan dalam mendapatkan informasi dengan sangat cepat. Manfaat dari perkembangan teknologi ini dapat dirasakan oleh semuassektor, termasuk sektor pemerintahan yang harus mengayomi masyarakat dan negara. Dalam meningkatkan kualitas pelayanan publik, pemerintah harus menerapkan pemerintahan yang berbasis teknologi informasi digital. Oleh karena itu, Pemerintah pusat maupun daerah telah menyediakan layanan pengaduan masyarakat yang berbasis online. Untuk meningkatkan kualitas pelayanan maka sistem pengaduan online harus berjalan dengan optimal. Metode yang banyak digunakan untuk mencari kemiripan teks pengaduan adalah metode cosine similarity dan metode Artificial Neural Network (ANN) untuk klasifikasi data pengaduan. Penelitian ini mereview penerapan kedua metode tersebut untuk mengetahui tingkat akurasinya sebelum dapat di implementasikan pada sistem pengaduan online. Hasil dari review menyatakan bahwa metode Cosine Similarity memiliki tingkat akurasi sebesar 71,5% dan ANN memiliki tingkat akurasi sebesar 77%. Sedangkan metode lainnya memiliki tingkat akurasi sebesar 67%. Dari presentase nilai tersebut dapat disimpulkan bahwa penggunaan metode Cosine Similarity dan ANN layak untuk digunakan dalam mengklasifikasikan data pada Sistem Pengaduan Masyarakat Online
Higher Education, or tertiary education, is the final stage which is optional in formal education. It is usually organized in the form of a university, academy, seminary, high school, or institute. Every tertiary institution needs qualified and professional educators because they have an important role in the process of implementing the Tri Dharma of Higher Education. Recruitment for teaching staff usually has several stages and standardization of assessment in selection proces. In order for the process of selecting educators to be carried out objectively, a support system is need to carry out the assessment process. This study applies the Fuzzy K-Nearest Neighbor (FK-NN) method for the classification process in determining prospective educators who pass or not. Data classification is a new data or object grouping into classes or labels based on certain attributes. The application of the FK-NN method has several stages, namely weighting the criteria, then calculating the closeness of the test data and training data, finding the value of k-nearest neighbors between the training data and testing data and determining the membership of each data. Tests were carried out using the Confusion matrix method on several variations of the k value where the highest percentage was obtained from the value of k = 5. The test results for all k values obtained an average accuracy rate of 89.22%, 89.22% precision and 82.45% recall with 114 training data and 50 test data. Based on the average value of the test results, it can be concluded that the FK-NN method is feasible and good to use for the selection of educators with the classification of pass or not.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.