Publication is an important tridharma activity for lecturers. This study aims to produce a clustering model using the K-Means algorithm which was built for ease of operation of publications. The method used is research and development which includes the stages of data collection, data preprocessing, clustering process and cluster analysis. The input data consists of 87 with 8 attributes, namely the number of journal articles indexed by Sinta, the number of journal articles indexed by Scopus, the number of citations in Scopus, the H-index in Scopus, the number of articles in indexed journals in Google Scholar, the number of citations in Google Scholar, the H-index in Google Scholar and H-index10 in Google Scholar. The K-Means algorithm is used with 3 clusters and 100 epochs. The clustering results are divided into 3 clusters, namely cluster 1 with 17 members, cluster 2 with 32 members and cluster 3 with 38 members. Clustering with 5 clusters produces cluster 1 with 5 members, cluster 2 with 12 members, cluster 3 with 20 members, cluster 4 with 18 and cluster 5 with 32 members. The results of the cluster analysis show that the clustering process with 3 clusters is improved and the academic application is better than clustering with 5 clusters.
Copyrights © 2022