Jurnal Ilmu Komputer dan Sistem Informasi

Implementasi Content-Based Filtering dan Singular Value Decomposition untuk Rekomendasi Film

Muhammad Iqbal Pradipta, Mhd. Basri — Mon, 27 Jul 2026 00:00:00 +0700

The growth of online video catalogs creates information overload that makes it difficult for users to discover movies matching their preferences. This study develops and evaluates two movie recommender approaches: content-based filtering using TF-IDF and cosine similarity, and collaborative filtering using Singular Value Decomposition (SVD). The dataset includes 4,803 movies with production-credit records and 100,004 user-rating interactions. The research stages comprise data cleaning and integration, content representation, latent-factor modeling, a 75:25 train-test split, and evaluation using Precision and Root Mean Squared Error. The content-based experiment achieved a Precision of 0.70 based on genre overlap, while director- and actor-based recommendations obtained a precision of 1.00 because the ranking features were identical to the relevance criteria. The SVD model achieved an RMSE of 0.9007 and generated personalized recommendations from user-rating patterns. The study contributes an evaluation of two baselines with different objectives, an analysis of potential bias in precision measurement, and an emphasis on consistent movie identifiers across datasets. Content-based filtering is effective for retrieving movies with similar metadata, whereas SVD captures latent user preferences. However, the results of the two approaches must be interpreted using metrics appropriate to their respective objectives.

Analisis Sentimen Berbasis Aspek pada Ulasan Aplikasi JConnect Mobile Menggunakan IndoBERT dan mBERT

Nadin Isna Monica, Abdul Rezha Efrat Najaf, Nambi Sembilu — Tue, 04 Aug 2026 00:00:00 +0700

JConnect Mobile is a mobile banking application developed by Bank Jatim that provides various digital banking transaction services. Although the number of users has continued to increase, the application still receives numerous complaints regarding its interface, features and performance, and service quality, as reflected in user reviews and its relatively low application rating. This study aims to compare the performance of the IndoBERT and mBERT models for aspect-based sentiment classification of JConnect Mobile user reviews. The dataset consists of 4,344 user reviews collected from Google Play Store and App Store between 2021 and 2025. The research methodology includes data collection, data labeling, preprocessing, feature extraction, modeling, and evaluation. The experiments were conducted using 5-fold cross-validation with 24 experimental scenarios involving combinations of hyperparameters, including 5 and 10 epochs, dropout rates of 0.2, 0.4, and 0.6, and batch sizes of 16 and 32. The results of the 5-fold cross-validation show that IndoBERT achieved the best performance, with mean F1-scores of 0.86 for the interface aspect, 0.83 for the features and performance aspect, and 0.74 for the service aspect. Based on these results, IndoBERT was selected as the best-performing model because it consistently outperformed mBERT across all aspects. Evaluation on the test dataset further demonstrated that the best-performing model achieved F1-scores of 0.80 for the interface aspect, 0.83 for the features and performance aspect, and 0.81 for the service aspect.

Implementasi Metode Weighted Moving Average dan Least Square Untuk Persediaan Obat Pada Apotek Kimia Farma

Anggreini Anggreini, Samsudin Samsudin — Thu, 06 Aug 2026 00:00:00 +0700

Drug inventory management is an important aspect of pharmacy services because it directly affects medicine availability for patients. Inaccurate inventory planning may lead to stock shortages (stockout) or excess inventory (overstock), which can reduce service quality and increase storage costs. This study aims to develop a drug inventory forecasting system for Kimia Farma Pharmacy using the Weighted Moving Average (WMA) and Least Square methods. The research employed the Research and Development (R&D) approach, while the system was developed using the Rapid Application Development (RAD) method. The dataset consisted of historical sales records of ten types of medicines from January to November 2023, collected through observation, interviews, and literature review. The results indicate that the developed system is capable of automatically forecasting future drug inventory based on historical sales data. The Weighted Moving Average method provides forecasts that are more responsive to recent demand changes by assigning greater weights to the latest observations, while the Least Square method generates forecasts based on sales trends. The developed system assists pharmacy staff in determining appropriate inventory levels, thereby reducing the risk of stock shortages and overstock situations. Therefore, the proposed forecasting system can improve the effectiveness of drug inventory management at Kimia Farma Pharmacy.

Desain dan Pengembangan Sistem Informasi Manajemen Proyek Berbasis Web di Apotek Cemara

Fikri Darojatul Ilmi, Purnomo Sidiq — Fri, 07 Aug 2026 00:00:00 +0700

Project management at Cemara Pharmacy faced challenges such as poor team coordination, progress monitoring difficulties, and data inaccuracies, hindering operational efficiency in the pharmaceutical sector. This study aimed to design and develop a web-based project management information system to support real-time planning, execution, and evaluation of projects. The research employed the Waterfall model, with data collection via field observations, interviews with managers and staff, document analysis, and literature review; the population comprised Cemara Pharmacy staff as primary participants, using UML (Use Case, Activity, Sequence, Class Diagrams), WBS, Gantt Chart, and PERT as instruments; data analysis involved functional, integration, and User Acceptance Testing (UAT). Results demonstrated that the Laravel- and MySQL-based system enhanced transparency, reduced administrative errors, and improved efficiency by up to 30%, with user evaluations highlighting interface ease and multi-platform accessibility. The study concludes that the system significantly contributes to professional project management in pharmacy SMEs, implying broader operational digital transformation.

Analisis Sentimen Debat Capres dan Cawapres Indonesia 2024 Menggunakan Metode Bert

Zaki Musyaffa, Mhd. Furqan, Aidil Halim Lubis — Thu, 20 Aug 2026 00:00:00 +0700

The 2024 Indonesian Presidential and Vice Presidential Candidate Debate, broadcast on the YouTube channel of the Indonesian General Elections Commission (KPU), generated thousands of public comments reflecting societal sentiment toward the candidates, yet these opinions have not been systematically examined. This study aims to analyze the sentiment of YouTube comments on the debate using the Bidirectional Encoder Representations from Transformers (BERT) method. A total of 2,500 comments were collected via the YouTube Data API from five debate sessions, then cleaned through a pre-processing stage and automatically labeled using the InSetLexicon dictionary into three categories: positive, negative, and neutral. After removing duplicate data, 2,362 clean records were obtained and divided into training and testing data with an 80:20 ratio. The IndoBERT model was then fine-tuned to classify comment sentiment. The results show that the sentiment distribution was dominated by positive comments (1,107), followed by negative (660) and neutral (595) comments. Model evaluation using a confusion matrix yielded an accuracy of 76.5%, with the highest precision, recall, and F1-score values in the positive class at 87.78%, 85.39%, and 86.57%, respectively. These findings indicate that the BERT method is fairly effective in analyzing the sentiment of Indonesian-language comments in the context of political debates on YouTube, while also contributing a mapping of public opinion toward candidates and debate issues that can serve as a reference for future Indonesian-language political sentiment analysis research.

Penerapan Algoritma K-Means Untuk Klasterisasi Pasien Berdasarkan Data Penyakit

Ghufron Makmun Lbs, Abdul Halim Hasugian — Fri, 21 Aug 2026 00:00:00 +0700

Sibuhuan Community Health Center (Puskesmas Sibuhuan) experiences a continuous increase in patient visit data every month. However, the utilization of these data is still limited to administrative reporting, resulting in the underutilization of information regarding patient group characteristics. This study aims to implement the K-Means algorithm for patient clustering and to identify patient characteristic patterns based on age, gender, and disease variables. This research employed a quantitative method with a data mining approach. The data used were secondary data consisting of 1,000 patient visit records from Puskesmas Sibuhuan during the January 2026 period. Following data cleaning, 104 records containing missing values were removed, resulting in 896 records used for the clustering process. The research stages included data preprocessing, Min-Max normalization, determining the optimal number of clusters using the Elbow Method, clustering using the K-Means algorithm, and evaluating the clustering results using the Silhouette Coefficient. The results showed that the optimal number of clusters was three, Cluster 0 consisted of 423 patients, predominantly diagnosed with diseases of the respiratory, digestive, and circulatory systems. Cluster 1 comprised 320 patients, with the most prevalent diagnoses involving symptoms, signs, and abnormal clinical findings, as well as pregnancy, childbirth, and the puerperium. Cluster 2 consisted of 153 patients, predominantly diagnosed with infectious and parasitic diseases, endocrine, nutritional and metabolic diseases, and mental and behavioral disorders. The evaluation produced a Silhouette Coefficient value of 0.6384, indicating that the clustering results were of good quality. The findings of this study are expected to provide supporting information for Puskesmas Sibuhuan in identifying patient group characteristics and to assist in planning more targeted healthcare services.