Kinerja pegawai menjadi rangkuman dalam hal kualitas, kuantitas, jam kerja dan juga kerja sama untuk mencapai suatu tujuan yang telah ditetapkan oleh instansi atau perusahaan, namun dalam Sekretariat DPRD Provinsi Sulawesi Utara belum adanya metode untuk menentukan pengelompokkan kinerja pegawai. Untuk mengatasi permasalahan ini, diperlukan adanya pengelompokan kinerja pegawai di Sekretariat DPRD Provinsi Sulawesi Utara, sehingga bisa menentukan kinerja pegawai yang berkualitas. Tujuan dari penelitian ini dengan melakukan perbandingan metode-metode clustering untuk mendapatkan metode yang lebih baik dalam pengelompokkan cluster terhadap kinerja pegawai di Sekretariat DPRD Provinsi Sulawesi Utara. Metode pengelompokkan data kinerja pegawai yang dibuat menggunakan metode clustering k-means, k-medoids, x-means dengan menggunakan lima atribut, yaitu: orientasi pelayanan, integritas, komitmen, disiplin, dan kerjasama, kemudian diolah dengan bantuan rapidminer, sehingga membagi data menjadi dua cluster yang dikategorikan sebagai nilai tinggi dan rendah. Pada tahap berikutnya mencari nilai davies bouldin index memakai bantuan rapidminer pada setiap metode yang dipakai untuk melakukan perbandingan serta menentukan metode yang lebih optimal dalam clustering. Hasil nilai yang diperoleh dari metode davies bouldin index di setiap algoritma, yaitu: k-means sebesar -0.377, k-medoids sebesar -0.930, dan x-means sebesar -0.497, maka algoritma terbaik untuk pengelompokkan data kinerja pegawai dalam penelitian ini adalah algoritma k-means, karena memiliki nilai DBI yang terkecil.
The PeduliLindungi application is an application launched by the government during the COVID-19 pandemic, with the aim of helping government agencies carry out digital tracking to monitor the public, as an effort to prevent the spread of the Corona virus. Many people express their opinions on the PeduliLindung application on social media, one of which is through Twitter. To improve the performance of the application, of course, need input or complaints from users, opinions from the public on Twitter about the PeduliLindungi application can be input to improve or improve the performance of the application. Sentiment analysis is carried out to see how the public's sentiment towards the PeduliLindung application is, and these sentiments will be categorized into positive sentiment and negative sentiment, this sentiment can later be used as evaluation material for application development. This study aims to see and compare the accuracy of two classification methods, Naïve Bayes and Support Vector Machine in the classification process of sentiment analysis. The data used are 4636 tweets with the keyword " PeduliLindungi". The data obtained then goes to the pre-processing stage before going to the classification stage. The results obtained after classifying using the Naïve Bayes method and the Support Vector Machine show that the Support Vector Machine method has a higher accuracy of 91%, while the Naïve Bayes method has an accuracy of 90%.
Based on the map of the spread of COVID-19 in Indonesia, Kalimantan Island is the second island with the number of COVID-19 distributions after Java Island. The purpose of this study is to provide information to the entire community and government, especially the Kalimantan region regarding the clustering of the spread of COVID-19. The K-Means algorithm method used in the grouping is based on data on positive, recovered, and deceased people collected by each province on the island of Kalimantan, then a geographic information system (GIS) is applied in mapping to display the clustered distribution area of each district on the island of Kalimantan. The result of this research is that the k-means algorithm is able to classify data with low, medium, and high distribution levels so that later the distribution area can be mapped using GIS based on the results of the clustering. With the results of this application, it is hoped that it can be used as information for the government and also the public to think about what efforts should be made if bad things happen later, based on the level of spread to be used as a priority scale in controlling the spread of the COVID-19 virus.
The logistical assistance’s distribution itself has problems in determining the shortest route which should be chosen properly. Dijkstra method can be applied in choosing the shortest route. Dijkstra method is a method that can determine the shortest route from the boarding point to the arrival point by the smallest weight, to display into a map, it needs Google Maps Api technology. It is a free service provided by google that can be accessed by a browser. This research resulted in application on logistical assistance’s distribution of natural disasters by applying dijkstra method on finding the shortest route.
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.