Article Per Year (5 Year)
p-Index From 2021 - 2026
1.829
P-Index
This Author published in this journals
All Journal PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Jurnal Komtika (Komputasi dan Informatika) Jurnal ICT : Information Communication & Technology Aisyah Journal of Informatics and Electrical Engineering Jurnal Sains Teknologi dalam Pemberdayaan Masyarakat Jurnal Manajemen Informatika Jayakarta Journal of Students‘ Research in Computer Science (JSRCS) Teknologi Informasi dan Digital (TRIDI)
Rasim Rasim
Informatika, Fakultas Ilmu Komputer, Universitas Bhayangkara Jakarta Raya
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology Other

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
The Weighted Product Method and the Multi-Objective Optimization on the Basis of Ratio Analysis Method for Determining the Best Customer Mugiarso Mugiarso; Rasim Rasim
PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Vol. 11 No. 1 (2023): March 2023
Publisher : LPPM Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/piksel.v11i1.6325

Abstract

The objective of this study is to compare the effectiveness of the Weighted Product (WP) and Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) methods in determining the best customers. Onesnet, the case study service provider, provides discounts and rewards to eligible customers to support this objective. The problem addressed in this study is how to determine the most relevant method for selecting eligible customers for bonuses. To achieve this, sensitivity testing was conducted by altering the weights of each criterion in both methods and observing the percentage changes of the results. The Weighted Product method multiplies the rating of each connected attribute, which is raised to the appropriate attribute weight, to decide. Data for this study was collected through interviews and observations at Onesnet and processed using the Rank Order Centroid (ROC) method for weighting, and the WP and MOORA methods for evaluating and selecting a decision. The WP and MOORA methods produced different total values and rankings, but the modeling with either method can be used equally for selecting the best customers. While there was a 60% similarity in data between the two methods, the WP method is recommended over MOORA, as it prioritizes customers with high loyalty criteria as the best customers.
Sentiment Analysis of Application Reviews using the K-Nearest Neighbors (KNN) Algorithm Damar Wijati; Prima Dina Atika; Siti Setiawati; Rasim Rasim
PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Vol. 12 No. 1 (2024): March 2024
Publisher : LPPM Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/piksel.v12i1.9490

Abstract

Product reviews play a crucial role in evaluating user satisfaction and overall performance. Vidio, one of the over-the-top (OTT) media platforms, offers a wide range of entertainment content, including movies, TV shows, sports events, music shows, lifestyle programs, and more, accessible through its application. Users have the opportunity to provide reviews and feedback on their experience with the Vidio application. Therefore, this research was conducted to analyze user sentiment towards the Vidio application on the Google Play Store platform using the K-Nearest Neighbors (KNN) method. Data for sentiment analysis were randomly selected from the Vidio application based on the most relevant reviews. A total of 3,000 data were analyzed, with 2,238 data in the negative class, 508 data in the neutral class, and 254 data in the positive class. This research used the K-Nearest Neighbors (KNN) method for classifying reviews based on negative, neutral, and positive classes, and the Multiclass Confusion Matrix for model evaluation. With a data split of 70% for training data 30% for testing data, and several n_neighbors of 10 data, the results in an accuracy of 81.6%, precision of 79%, recall of 81.6%, and F1-Score of 77%.
Co-Authors Anida Nurmalisa Aryo Juliano Asep Ramdhani Damar Wijati Dwipa Handayani Dwipa Handayani Hantoro, Kusdarnowo Hendarman Lubis Herlawati Herlawati Irsyad Rawinto Krisna Dimas Pujiono M. Hadi Prayitno Mugiarso Mugiarso Mugiarso Mugiarso Muhammad Khaerudin Oriza Sativa Dinauni Silaen Prima Dina Atika Siti Setiawati Sugiyatno Sugiyatno