Zona Komputer: Program Studi Sistem Informasi Universitas Batam

A COMPARATIVE STUDY OF CNN-BILSTM AND TF-IDF–NAIVE BAYES FOR SENTIMENT CLASSIFICATION ON MOVIE REVIEWS: PERFORMANCE AND EFFICIENCY TRADE-OFFS

2026-08-11T11:50:06+08:00

Sentiment analysis on movie reviews has become an important task for understanding public opinion, yet many high-performing deep learning models proposed in the literature rely on increasingly complex architectures such as multichannel embeddings, kernel-based projections, or attention-augmented transformers. This added complexity often comes without a clear report of computational cost, making it difficult to judge whether the performance gain justifies the resource trade-off. This study investigates whether a deliberately simplified Convolutional Neural Network combined with a Bidirectional Long Short-Term Memory (CNN-BiLSTM) architecture can achieve competitive performance compared to a classical baseline, TF-IDF combined with Naive Bayes, while explicitly reporting training efficiency. Both models were trained and evaluated on the IMDB Dataset of 50,000 movie reviews, split into 80% training, 10% validation, and 10% testing sets. Experimental results show that the proposed CNN-BiLSTM achieved an accuracy of 86.58%, precision of 90.38%, recall of 81.88%, F1-score of 85.92%, and AUC of 0.946, while the TF-IDF-Naive Bayes baseline achieved an accuracy of 85.98%, precision of 86.58%, recall of 85.16%, F1-score of 85.86%, and AUC of 0.932. The proposed method required approximately 203 seconds of training time, compared to 0.07 seconds for the baseline. These findings indicate that the performance improvement offered by the deep learning approach is modest relative to its substantially higher computational cost, providing practical guidance for method selection in resource-constrained settings.

EVALUASI KUALITAS VISUAL DAN EFISIENSI KOMPRESI: JPEG VS CONVOLUTIONAL AUTOENCODER (CAE) PADA DATASET DIV2K

2026-08-11T11:54:21+08:00

Image compression is a fundamental technique in digital image processing aimed at reducing storage space requirements and transmission bandwidth without excessively sacrificing visual quality. As the volume of image data grows dramatically, driven by the expansion of social media platforms, intelligent surveillance systems, and medical imaging applications, the need for efficient and adaptive compression methods becomes increasingly critical. This study presents a comparative evaluation between JPEG, the industry standard based on Discrete Cosine Transform (DCT), and Convolutional AutoEncoder (CAE) based on deep learning, using the DIV2K benchmark dataset (799 high-resolution images, 80:20 train-test split). The proposed CAE architecture employs a 16×16 spatial convolutional bottleneck in two capacity variants: ch=64 (BPP=2.0, CR=12×) and ch=128 (BPP=4.0, CR=6×). Evaluation was conducted using five quantitative metrics: PSNR, SSIM, MSE, BPP, and Compression Ratio, reported as mean ± standard deviation (N=100). Experimental results demonstrate that JPEG still outperforms CAE quantitatively, achieving a peak PSNR of 37.104 ± 3.469 dB at Q=90, while the best CAE variant reaches only 20.703 ± 4.453 dB. This performance gap is attributed to limited training data, simplified architecture, and the absence of explicit rate-distortion optimization. This study provides a rigorous, reproducible quantitative evaluation framework as a baseline for future deep learning-based image compression research.

PERANCANGAN UI/UX APLIKASI "MY CATATAN GWEH" SEBAGAI MEDIA PENCATATAN AKTIVITAS DAN MANAJEMEN KEUANGAN PRIBADI BERBASIS MOBILE

2026-08-11T12:00:29+08:00

Penelitian ini memaparkan proses perancangan user interface dan user experience (UI/UX) aplikasi "My Catatan Gweh", sebuah aplikasi mobile yang dirancang untuk menggabungkan pencatatan aktivitas harian dengan manajemen keuangan pribadi dalam satu platform. Proses perancangan mengikuti kerangka Design Thinking, dimulai dari tahap empathize berupa penggalian kebutuhan secara kualitatif melalui wawancara terbuka kepada sembilan responden yang dipilih secara purposif. Temuan menunjukkan bahwa mayoritas responden saat ini mengelola catatan aktivitas dan keuangan pribadi pada aplikasi yang terpisah, yang menimbulkan beban kognitif dan navigasi tambahan akibat perpindahan konteks antaraplikasi, serta menyatakan preferensi terhadap satu aplikasi yang sederhana dan minim iklan yang menggabungkan kedua fungsi tersebut. Temuan ini menjadi dasar tahap define dan ideate, yang menghasilkan usulan navigasi bottom-tab dua modul (Catatan dan Dompet) yang kemudian diterjemahkan ke dalam wireframe tingkat rendah, high-fidelity design, dan akhirnya diimplementasikan sebagai prototipe Android fungsional berbasis framework Flutter, melampaui sebatas mockup interaktif statis yang umum dihasilkan pada penelitian sejenis. Setiap keputusan desain ditelusuri secara eksplisit terhadap kebutuhan pengguna yang teridentifikasi pada tahap empathize sebagai bentuk validasi UX berbasis pemenuhan kebutuhan, sementara pengujian usability empiris formal seperti System Usability Scale (SUS) diposisikan sebagai aktivitas tahap test lanjutan untuk penelitian berikutnya.

PERANCANGAN UI/UX APLIKASI MOBILE KEDAI KOPI CEI BERBASIS DESIGN THINKING

2026-08-11T11:56:48+08:00

This study presents the design of a mobile user interface and user experience (UI/UX) for Kedai Kopi Cei, a modern coffee shop, using the Design Thinking approach. The research addresses five key pain points identified during the Empathize stage: inefficient manual ordering, limited real-time menu and promotion information, the absence of a digital seat-reservation system, the lack of a measurable loyalty program, and the absence of order-tracking features. Through the five stages of Design Thinking—Empathize, Define, Ideate, Prototype, and Test—the study produced four user flows, a flat navigation map with five bottom-navigation tabs, eight low-fidelity wireframes, and twenty-two high-fidelity screens designed in Figma with an interactive prototype. Usability testing using the System Usability Scale (SUS) was conducted with five respondents aged 18–27. The results show an average SUS score of 70.0, placing the prototype in the Acceptable category (Grade C), above the usability threshold of 68 commonly cited in the literature. These findings indicate that the prototype is generally well received by users, while also revealing specific areas—visual hierarchy and navigation consistency—that require further refinement before technical development.

UI/UX Design; Design Thinking; Mobile Application; Usability Testing; System Usability Scale

SIMULASI DAN PEMODELAN BIG DATA ANALYTICS DALAM CRM E-COMMERCE INDONESIA

2026-08-26T10:28:55+08:00

Pertumbuhan sektor e-commerce Indonesia menghasilkan volume data pelanggan yang melampaui kapasitas analitik sistem Customer Relationship Management (CRM) konvensional, namun masih sedikit penelitian yang memodelkan hubungan tersebut pada data yang transparan dan dapat direproduksi. Penelitian ini menyusun kerangka simulasi dan pemodelan Big Data Analytics (BDA) dalam pengambilan keputusan CRM, dengan Tokopedia sebagai rujukan studi kasus. Dataset sintetis 5.000 pelanggan dibangkitkan dan dikalibrasi dengan Python berdasarkan pola pada literatur terdahulu serta statistik e-commerce nasional, kemudian diproses melalui statistik deskriptif, regresi logistik, dan klasterisasi K-Means. Model yang dihasilkan mengidentifikasi empat segmen pelanggan dengan probabilitas churn mulai dari 3,7 persen pada pelanggan loyal premium hingga 27,3 persen pada pemburu diskon, dengan skor kepuasan sebagai prediktor terkuat pada akurasi klasifikasi 82 persen. Hasil ini menunjukkan bahwa strategi retensi per segmen yang dibangun di atas model simulasi yang interpretatif dapat menjadi dasar pengambilan keputusan CRM sekalipun data transaksi riil tidak dapat diakses peneliti eksternal. Penelitian ini menyumbangkan alur simulasi dan pemodelan yang dapat direproduksi, menghubungkan segmentasi pelanggan, prediksi churn, dan Undang-Undang Pelindungan Data Pribadi ke dalam satu kerangka pengambilan keputusan bagi praktisi CRM.

Kata Kunci: Big Data Analytics, CRM, pemodelan simulasi, prediksi churn, segmentasi pelanggan