Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal Teknik Informatika (JUTIF)
Safitri Juanita
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
K-MEANS CLUSTERING WITH COMPARISON OF ELBOW AND SILHOUETTE METHODS FOR MEDICINES CLUSTERING BASED ON USER REVIEWS Safitri Juanita; Cahyono, Raynaldi Dwi
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 1 (2024): JUTIF Volume 5, Number 1, February 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.1.1349

Abstract

The dissemination of medicine information allows users or customers to make massive assessments of medicines, containing positive and negative reviews—one of a site that provides medicine information online, named drugs.com, contains reviews and ratings of each medicine by variant disease. This site has extensive data collection that has not been processed to produce helpful information for medicine information seekers or the medicine industry. Therefore, research is needed to cluster medicines based on data review from drugs.com. The contribution of this study proposes the best model to cluster user reviews for medicines using K-Means by comparing 2 (two) techniques to determine the optimal number of clustering, Silhouette and Elbow. This study aims to recommend the best K-Means clustering method for processing extensive data reviews and ratings, and cluster results help medical experts, medicine information seekers, or pharmaceutical businesses determine the market share of medicines. The results show that the K-Means model performs best when clustering using the Silhouette method with a DBI value of 0.261 and producing 2 clusters. Meanwhile, the Elbow model has the best performance value of 0.460 and produces 3 clusters. This study also shows that clustering results with both methods produce three medicine cluster groups based on reviews: moderate, unpopular and famous.
Co-Authors Cahyono, Raynaldi Dwi