cover
Contact Name
Muhammad Wali
Contact Email
journal@stmiki.ac.id
Phone
+62651-7552408
Journal Mail Official
jimik@stmiki.ac.id
Editorial Address
Jl. Teuku Nyak Arief No. 400 Jeulingke Banda Aceh
Location
Kota banda aceh,
Aceh
INDONESIA
Jurnal Indonesia : Manajemen Informatika dan Komunikasi
ISSN : 27768074     EISSN : 27237079     DOI : https://doi.org/10.35870/jimik
Core Subject : Science, Education,
Jurnal Indonesia: Manajemen Informatika dan Komunikasi is a scholarly publication dedicated to advancing the fields of information technology and communication management in Indonesia. The journal serves as a platform for researchers, academicians, practitioners, and policymakers to share their insights, knowledge, and expertise in these domains. This journal is a peer-reviewed online journal dedicated to high-quality research publications focused on research, implementation. Jurnal Indonesia: Manajemen Informatika dan Komunikasi is a scholarly publication dedicated to advancing the fields of information technology and communication management in Indonesia.
Articles 782 Documents
Implementasi Algoritma Hybrid CNN-ViT (LeViT-128) dalam Klasifikasi Motif Batik Indonesia Kevin Novebrianto; Hadi Zakaria
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 7 No. 3 (2026): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v7i3.2087

Abstract

Batik is an Indonesian cultural heritage featuring a wide variety of motifs with high inter-class visual similarity. The visual and manual identification process is highly subjective and inefficient. To address this classification problem, this study implements a deep learning approach using a hybrid Convolutional Neural Network (CNN) and Vision Transformer (ViT) architecture, specifically the LeViT model. This integration aims to synergize CNN's ability to extract local features—such as lines and dots—with ViT's self-attention mechanism to capture global spatial context efficiently. The research methodology follows the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework. The model was trained on a dataset of 5,292 images covering 39 batik motif classes. To address data imbalance, class weight adjustments and image augmentation techniques were applied. Based on the final evaluation using the One-vs-Rest approach on the test set, the model achieved an overall accuracy of 90.05% and a Weighted F1-Score of 89.84%, demonstrating the effectiveness and reliability of the hybrid CNN-ViT algorithm in classifying batik motifs with high visual complexity.
Rancang Bangun Aplikasi Pemesanan Menu Makanan dan Minuman Berbasis Web Berdasarkan Kebutuhan Pengguna pada Resto Rira Menggunakan Metode Design Thinking Chrystofer Nofriyanto; Muhammad Arman; Indra Samsie; Suci Ramadhani Arifin
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 7 No. 3 (2026): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v7i3.2097

Abstract

Manual ordering at Resto Rira, which is located near a university campus, increases the service burden during peak hours. This study aimed to design and develop a web-based menu-ordering application based on user needs through the five stages of Design Thinking. Data were collected through direct observation and semi-structured interviews lasting 10–15 minutes with nine informants: five customers, two waiters, one cashier, and one owner. The Empathize and Define stages identified needs for self-ordering through table QR codes, menu information, payment, order-status tracking, and operational management. Limited prototype trials involved two customers, two waiters who were not researchers, and one cashier. Descriptively, all participants completed the main task flow according to their roles. Customers accessed the menu without waiting for a waiter to provide it, waiters monitored orders through a centralized list, and the cashier traced payment and transaction information. Black Box testing of 60 scenarios showed that the outputs matched the expected results in 100% of cases. These findings demonstrate the application’s initial functional feasibility but do not establish improved operational efficiency or quantitative usability. Study limitations include the absence of waiting-time and recording-error measurements, the limited user-trial sample, and the lack of testing for failed payments and concurrent stock transactions.
Analisis Sentimen Teks Komentar Produk Skincare Menggunakan Model IndoBERT Ratna Juwita; Heri Suroyo
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 7 No. 3 (2026): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v7i3.2098

Abstract

The rapid growth of the local skincare industry in Indonesia has intensified consumer interactions on Instagram and TikTok, generating a substantial volume of comments that are inefficient to analyze manually. This study aims to implement the IndoBERT model to classify sentiment in beauty product comments using the CRISP-DM framework. A total of 5,062 comments from five local brands (Somethinc, MS Glow Beauty, Avoskin, N.Pure, and SkinGame) were retrieved via web scraping and automatically labeled into positive and negative classes using a lexicon-based approach. The evaluation results demonstrate that the fine-tuned IndoBERT model achieved an accuracy of 87% under the 80:20 data-splitting scenario and 86% under the 75:25 scenario. In the 75:25 scenario, the model attained a precision of 84%, recall of 94%, and F1-score of 89%, while remaining free from overfitting as shown by the loss curve. In conclusion, the IndoBERT architecture demonstrates high reliability in classifying consumer sentiments despite challenges from slang, dermatological terms, and code-mixing.
Implementasi Term Frequency dan Cosine Similarity pada Aplikasi Koreksi Otomatis Jawaban Esai Berbasis Web Joko Suwarno; Galuh Saputri; Willis Puspita Sari; Didik Kusuma Rahmat
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 7 No. 3 (2026): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v7i3.2101

Abstract

Manually grading essay answers is time-consuming and labor-intensive, as teachers must review each student's response individually against an answer key. This study aims to implement Term Frequency (TF) and Cosine Similarity within a web-based automated essay grading application. The system was developed using the Waterfall Software Development Life Cycle (SDLC) model, with text processing involving case folding, tokenization, filtering, and stemming stages. Preprocessing results were represented as term frequencies and subsequently compared using Cosine Similarity. A sample calculation using a single pair—an answer key and a student response—yielded a Cosine Similarity score of 0.878 (87.8%), indicating the level of textual similarity between the two documents; this figure does not represent the system's overall accuracy, as algorithm testing in this study was limited to a single document pair and did not include a comparison with teacher assessments. Functional testing using Black Box Testing demonstrated that the application's core functions operated according to the designed scenarios. The results indicate that TF and Cosine Similarity can be implemented as a mechanism for measuring textual similarity in web-based essay grading applications. Validation using a larger dataset of student answers and comparisons with teacher assessments is required to evaluate the method's performance more comprehensively.
Perancangan Sistem E-Rapor PAUD dengan Otomatisasi Deskripsi Perkembangan Anak Menggunakan Pendekatan Agile Software Development Wiwin Winarti; Dawam Agung Pribadi
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 7 No. 3 (2026): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v7i3.2108

Abstract

Early childhood education (ECE) teachers must report each child's progress as a developmental narrative rather than numeric scores. At PAUD Lily, Depok, these narratives were written manually for every child, which was time-consuming and inconsistent. This study designs a web-based ECE e-report system that automatically composes draft developmental descriptions from teachers' assessment data as soon as the teacher selects an achievement level, built with Agile Software Development in three iterations. Its main contribution is a rule-based engine that selects teacher-curated paragraphs from a sentence bank according to each aspect and achievement level (BM, MM, SM, BSH, BSB), producing consistent narratives that teachers can still edit. Black-box testing of 12 scenarios confirmed that all features work as designed, and engine verification showed outputs consistent with the mapping rules for the tested combinations. Teachers remain the final editors; measuring their acceptance of the generated descriptions is left for future work.
Strategi Komunikasi Pemasaran Digital Berbasis Model AISAS dalam Meningkatkan Keputusan Pembelian pada Lare Coffee Shop Space: Studi Kasus Surya Kusdeva; Muhammad Najih Farihanto
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 7 No. 3 (2026): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v7i3.2109

Abstract

This study aims to analyze the digital marketing communication strategy applied by Lare Coffee Space in increasing purchase decisions, using the AISAS (Attention, Interest, Search, Action, and Share) model. The central question addressed is how each stage of the model functions as a unit of analysis in various digital marketing practices in Indonesia, and what factors support the success of its implementation. This research employed a descriptive qualitative approach with a case study design, collecting data through field observation, digital observation, in-depth interviews, and documentation at the research site. Data analysis was conducted through thematic content analysis by categorizing findings into the five constructs of the AISAS model, while data validity was tested through source triangulation and intertextual checking. The findings show that the success of Lare Coffee Space in increasing sales volume was supported by the integrated application of all five stages: paid digital advertising and collaboration with culinary influencers, persuasive and educational content with attractive product aesthetics, optimized social media profiles, convenient payment systems, and the creation of a shareable store atmosphere. This study offers a theoretical contribution through the synthesis of the AISAS model as an analytical framework for digital marketing communication, along with practical implications for local coffee shop managers in designing more targeted and sustainable marketing strategies.
Sistem Informasi Manajemen Stok Berbasis Web Menggunakan Average Cost dan Pencatatan Hybrid Khoirul Umam; Suyanto Suyanto
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 7 No. 3 (2026): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v7i3.2110

Abstract

Manual inventory management at Barokah Electronics Store, Pasar 16 Ilir Palembang, poses risks of recording errors, stock discrepancies, and inaccurate cost determination. This study developed a web-based inventory management information system using Average Cost and hybrid recording, which combines perpetual and periodic recording. Design Science Research (DSR) was used as the research approach, while Rapid Application Development (RAD) guided artifact development through Requirement Planning, User Design, Construction, and Cutover. Average Cost was used to update the average cost when incoming purchases had different prices. Items with acquisition costs above IDR 500,000 were recorded perpetually, whereas items with acquisition costs of up to IDR 500,000 were recorded periodically and reconciled through Stock Opname. Black Box Testing with Katalon Studio documented seven main test cases with PASSED status. Implementation evidence showed that the system displayed average cost values and recorded differences between system and physical quantities during Stock Opname. The study did not measure changes in stock discrepancies before and after implementation, user acceptance, or system performance under large-scale actual transactions. Its findings are therefore limited to the implementation of business logic and documented functional testing.
Pengembangan Aplikasi Question Answering Berbasis Retrieval-Augmented Generation Menggunakan Qwen3-8B untuk Pencarian Informasi Toko Elektronik di Palembang Dhini Novely Saputri; Heri Suroyo; Leon A. Abdillah; M. Soekarno Putra
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 7 No. 3 (2026): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v7i3.2111

Abstract

Large Language Models (LLMs) can generate fluent responses but may produce unsupported answers in domain-specific settings. This study developed and evaluated a question answering application for electronic-store information retrieval in Palembang by integrating Qwen3-8B with Retrieval-Augmented Generation (RAG). Using Design Science Research, the study produced a web application supported by a knowledge base of 1,019 product records from eight stores. Each record contained six attributes: store name, address, telephone number, Google Maps link, category, and product name. The data were converted into 768-dimensional embeddings using sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 and stored in ChromaDB. The system retrieved the top five records based on cosine similarity and applied a 0.65 threshold before supplying context to Qwen3-8B through the Groq API. Evaluation used 200 queries; positive labels indicated available information, whereas negative labels indicated unavailable or out-of-scope information. Responses were classified as true positives (TP) when positive queries were answered correctly, true negatives (TN) when negative queries were rejected correctly, false positives (FP) when negative queries received answers, and false negatives (FN) when positive queries were rejected or not answered. Testing yielded TP=143, TN=5, FP=34, and FN=18, with 74.00% accuracy, 80.79% precision, 88.82% recall, and an 84.61% F1-score. Errors occurred with short ambiguous queries, semantic overlap, local terminology, and typographical variation. RAG supplied retrieved context as the basis for responses, but rejection of queries outside the knowledge base remains limited.
Eksistensi Wayang Wong di RRI Surakarta sebagai Media Komunikasi Budaya pada Era Digitalisasi Nur Septaningrum; Novianti Novianti
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 7 No. 3 (2026): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v7i3.2113

Abstract

This study aims to analyze the existence of the Wayang Wong program on RRI Surakarta as a medium of cultural communication in the digital age. This study employs a qualitative approach with informants consisting of one Wayang Wong puppeteer from RRI Surakarta and one listener of the Wayang Wong program. Data collection was conducted through in-depth interviews, observation, documentation, and literature review over a two-week period. The data were analyzed descriptively by grouping the findings based on Harold D. Lasswell’s media functions, which include environmental monitoring, social correlation, and the transmission of cultural heritage, as well as the entertainment function proposed by Charles R. Wright. Observations and documentation were conducted regarding the broadcast’s implementation and the utilization of RRI Surakarta’s official online channels as a form of broadcasting adaptation in the digital era. The research results indicate that Wayang Wong on RRI Surakarta continues to function as a medium of cultural communication by conveying Javanese moral values, ethics, and culture through stories, characters, dialogue, and musical elements. From the listeners’ perspective, the existence of the Wayang Wong program provides access to Javanese cultural performances and information through both radio and digital channels. Adapting to digital media is one of RRI Surakarta’s efforts to maintain the transmission of cultural heritage to the public amid changing patterns of media consumption.
Strategi Komunikasi Penyiar Berita dalam Meningkatkan Kejelasan dan Pemahaman Informasi pada Program Siaran Pro 1 RRI Surakarta Nur Anisa Qhoirunnikmah; Novianti Novianti
Jurnal Indonesia : Manajemen Informatika dan Komunikasi Vol. 7 No. 3 (2026): September
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63447/jimik.v7i3.2114

Abstract

This study aims to analyze the communication process used by broadcasters in conveying news information to listeners on the Pro 1 RRI Surakarta broadcast program. This study employs a qualitative approach using descriptive methods. Data were collected through interviews, observations, and documentation during February–March 2026. The research informants consisted of two Pro 1 RRI Surakarta broadcasters and listeners who were involved in interactions during the broadcast. Observations were conducted on the preparation and execution of the broadcast as well as the broadcasters' interactions with listeners. Data were analyzed using Lasswell's Communication Theory and Source Credibility Theory to identify the elements of communication and the broadcasters' credibility in conveying information. The results indicate that the broadcasters' communication process encompasses the elements of communicator, message, medium, audience, and effect. The broadcasters delivered news information via radio by adapting their language, intonation, and communication style to the diverse characteristics of the listeners. Listener engagement was evident through telephone interactions during five live broadcast sessions, with each interaction lasting approximately two minutes. These responses served as indicators of listeners' interactive engagement in the communication process. During the live broadcasts, technical challenges—such as network disruptions and issues with listeners' telephone connections—required the broadcasters to make adjustments on the air. The broadcasters' credibility was reflected in their mastery of the subject matter, their ability to build trust, and their ability to engage listeners when conveying information. These findings indicate that a broadcaster's communication strategies play a role in ensuring clear delivery of information and fostering interaction with listeners.