cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Noviyanti. P
Contact Email
ti@shantibhuana.ac.id
Phone
+6285750550228
Journal Mail Official
ti@shantibhuana.ac.id
Editorial Address
Jalan Bukit Karmel No.1 Sebopet Kec. Bengkayang Kab. bengkayang Provinsi Kalimantan Barat, 79211
Location
Kab. bengkayang,
Kalimantan barat
INDONESIA
Journal of Information Technology (JIfoTech)
Published by Institut Shanti Bhuana
ISSN : 27744884     EISSN : 27756734     DOI : https://doi.org/10.46229/jifotech.v1i1
Core Subject : Science,
Computer Science & IT
Journal of Information Technology (JIfoTech) contains research articles in the scope of information technology, in the form of Internet of Things (IoT), web technology, databases, artificial intelligence, business intelligence, security and network infrastructure, human and computer interaction (HCI), data mining, and digital image processing.
Arjuna Subject : Ilmu Komputer (semua kategori) - Jaringan Komputer dan Komunikasi
Articles 86 Documents
 5   6   7   8   9 
Analisis Sentimen Layanan Akademik Civitas – Suteki Menggunakan Metode Naïve Bayes Hilmi Rahmawati; Nuk Ghurroh Setyoningrum
Journal of Information Technology Vol. 6 No. 2 (2026): Journal of Information Technology
Publisher : Institut Shanti Bhuana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46229/jifotech.v6i2.1133

Abstract

Penelitian ini bertujuan untuk menganalisis sentimen pengguna terhadap aplikasi layanan akademik Civitas–Suteki guna memahami bagaimana pengguna merespons dan mengalami penggunaan aplikasi tersebut. Tingginya proporsi ulasan negatif yang mencapai lebih dari sepertiga total data mengindikasikan perlunya evaluasi sistematis terhadap kualitas layanan aplikasi. Data dikumpulkan melalui teknik web scraping pada Google Play Store, menghasilkan 534 ulasan pada rentang Maret 2020 hingga April 2026. Proses preprocessing meliputi penghapusan duplikat, cleaning, case folding, tokenizing, stopword removal, dan stemming. Pembobotan kata menggunakan TF-IDF dan klasifikasi dilakukan dengan algoritma Multinomial Naive Bayes. Dari 473 ulasan valid, sebanyak 291 ulasan (61,52%) bersentimen positif dan 182 ulasan (38,48%) bersentimen negatif. Model mencapai akurasi sebesar 78,26%, dengan precision 0,79, recall 0,87, dan F1-score 0,83 untuk kelas positif, serta precision 0,77, recall 0,65, dan F1-score 0,71 untuk kelas negatif. Hasil ini menunjukkan bahwa metode Multinomial Naive Bayes dengan pembobotan TF-IDF efektif digunakan dalam klasifikasi sentimen ulasan berbahasa Indonesia dan dapat menjadi bahan evaluasi bagi pengembang aplikasi untuk meningkatkan kualitas layanan.
Klasifikasi Penyakit Daun Jagung Menggunakan MobileNet V3 Berbasis Transfer Learning Dengan Visualisasi Grad-CAM Rendhita Dennis Saputra; Afu Ichsan Pradana; Sopingi
Journal of Information Technology Vol. 6 No. 2 (2026): Journal of Information Technology
Publisher : Institut Shanti Bhuana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46229/jifotech.v6i2.1140

Abstract

Tanaman jagung merupakan komoditas pertanian strategis di Indonesia yang rentan terhadap serangan penyakit daun seperti Gray Leaf Spot, Northern Leaf Blight, dan Common Rust yang dapat menurunkan hasil panen secara signifikan apabila tidak ditangani sejak dini. Proses identifikasi yang masih dilakukan secara konvensional sangat bergantung pada pengalaman individu dan rentan terhadap kesalahan diagnosis, sementara model deep learning yang telah dikembangkan umumnya bersifat black-box sehingga sulit dipahami oleh pengguna akhir seperti petani dan penyuluh pertanian. Penelitian ini bertujuan mengembangkan model klasifikasi penyakit daun jagung yang akurat sekaligus interpretatif menggunakan arsitektur MobileNetV3-Small berbasis transfer learning dengan integrasi visualisasi Grad-CAM untuk meningkatkan transparansi hasil prediksi. Dataset yang digunakan terdiri atas 4.000 citra daun jagung dari platform Kaggle yang terbagi ke dalam empat kelas yaitu Bercak Daun, Hawar Daun, Karat Daun, dan Daun Sehat dengan rasio pembagian 80:20, dilatih selama 10 epoch menggunakan optimizer Adam dengan learning rate 0,001 dan batch size 32, serta diimplementasikan dalam prototipe aplikasi berbasis web menggunakan framework Flask. Hasil evaluasi menunjukkan model mencapai akurasi 97,75%, precision 97,76%, recall 97,75%, dan F1-score 97,75%, sementara evaluasi kuantitatif Grad-CAM pada 4.000 citra menghasilkan performa keseluruhan sebesar 98,55%, membuktikan relevansi visualisasi terhadap area gejala penyakit yang sebenarnya.
Kendali Adaptif Lingkungan Anggrek Dendrobium Berbasis Environment Score Menggunakan Pico W Andriaman Telaumbanua; Gogor Christmass Setyawan; Agustinus Rudatyo Himamunanto
Journal of Information Technology Vol. 6 No. 2 (2026): Journal of Information Technology
Publisher : Institut Shanti Bhuana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46229/jifotech.v6i2.1142

Abstract

The cultivation of Dendrobium orchids has high economic value but is highly dependent on the stability of microclimate parameters, specifically temperature, humidity, and light intensity. One of the common challenges faced by cultivators is the limitation of accurate and continuous monitoring systems, as well as the relatively high installation and operational costs of industrial-scale automation systems. This study aims to develop an Internet of Things (IoT)-based microclimate monitoring and control system using the Raspberry Pi Pico W, which is designed to be more economical, plug-and-play, and energy-efficient. The method employed utilizes the Environment Score algorithm to evaluate environmental conditions through multi-parameter analysis (temperature, humidity, and light), along with a pulse control technique on the humidifier actuator to prevent humidity overshoot during the actuation process. The system is also equipped with a buzzer-based early warning mechanism and real-time data logging capabilities transmitted directly to Google Sheets via HTTP protocol. The functional test results using Black Box testing methods on 2,787 recorded data rows, including extreme anomaly simulations (drastic temperature spikes and humidity drops), indicate that the system is highly responsive to critical conditions and capable of maintaining environmental stability with a logical response success rate of up to 99%. The pulse control method successfully minimizes extreme fluctuations. Therefore, the developed system has proven to be effective, adaptive, and low-cost in supporting the environmental management of Dendrobium orchid cultivation.
Integrasi ABSA dan LDA untuk identifikasi opini publik Kabupaten Pakpak Bharat Samuel Rama Silo Padang; Sunneng Sandino Berutu; Yoel Pieter Sumihar
Journal of Information Technology Vol. 6 No. 2 (2026): Journal of Information Technology
Publisher : Institut Shanti Bhuana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46229/jifotech.v6i2.1144

Abstract

Penelitian ini mengusulkan pendekatan Aspect-Based Sentiment Analysis (ABSA) yang mengintegrasikan Latent Dirichlet Allocation (LDA) dan IndoBERT untuk menganalisis opini publik terhadap Kabupaten Pakpak Bharat berdasarkan 4.591 tweet yang dikumpulkan melalui scraping. Data diproses melalui case folding, penghapusan URL dan mention, serta penyaringan stopword yang mempertimbangkan konteks. LDA digunakan untuk membangun taksonomi topik secara otomatis yang terdiri atas tujuh kategori, yang menjadi dasar ekstraksi aspek berbasis aturan menggunakan mekanisme pembobotan kata kunci dengan batasan taksonomi. Aspek dengan data yang tidak memadai digabungkan ke dalam kategori induk yang relevan secara semantik, menghasilkan sembilan kelas aspek akhir. Untuk mengatasi ketidakseimbangan kelas sentimen, diterapkan strategi random oversampling berbasis threshold, di mana setiap kelas minoritas ditingkatkan jumlahnya hingga nilai minimum antara ukuran kelas mayoritas dan nilai maksimum antara jumlah data saat ini atau 30% dari ukuran kelas mayoritas—sehingga dataset menjadi lebih seimbang dengan total 4.755 sampel tanpa menyamakan seluruh kelas secara penuh. Klasifikasi sentimen dilakukan menggunakan arsitektur multitask IndoBERT dengan dua classification head, di mana head aspek dilatih secara bersamaan menggunakan Focal Loss sebagai komponen pendukung untuk memperkuat representasi bersama, sementara label aspek akhir ditentukan melalui mekanisme berbasis aturan tersebut. Tiga aspek dengan volume pembahasan tertinggi adalah Keamanan (1.354 data), Sosial (1.313 data), dan Pariwisata (794 data). Model klasifikasi sentimen menunjukkan performa yang baik, dengan akurasi 85,59%, presisi 84%, recall 86%, dan F1-score 85%. Hasil ini menunjukkan bahwa integrasi LDA, ekstraksi berbasis aturan, dan IndoBERT efektif dalam memetakan persepsi publik secara granular, serta memberikan wawasan yang dapat ditindaklanjuti bagi evaluasi pemerintah daerah.
Analisis Sentimen Berbasis Aspek pada Ulasan Google Maps Restoran Soramen Menggunakan IndoBERT-LoRa Rafiq Satria Yudha; Sopingi; Moh. Muhtarom
Journal of Information Technology Vol. 6 No. 2 (2026): Journal of Information Technology
Publisher : Institut Shanti Bhuana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46229/jifotech.v6i2.1145

Abstract

Online reviews on Google Maps are a strategic resource for restaurant management, but a single review often praises one aspect while criticizing another, so document-level sentiment cannot reveal which aspect drives satisfaction or complaints. This study applies Aspect-Based Sentiment Analysis (ABSA) to Soramen restaurant reviews through a two-stage span-level pipeline—aspect-term extraction (ATE) then sentiment classification (ASC)—across four aspects (FOOD, SERVICE, PRICE, PLACE) with IndoBERT, evaluating parameter-efficient Low-Rank Adaptation (LoRA) against full fine-tuning to map critical service aspects. The data comprise 1,742 original reviews (3,930 spans) expanded to 3,061 reviews through controlled synonym-replacement augmentation and split using StratifiedGroupKFold with five folds. The results show that LoRA r=16 attains a Joint Partial F1 of 0.7744 with only 0.48% of parameters trained, comparable to full fine-tuning (0.7727); the difference is not statistically significant (paired t-test, p=0.82), so LoRA r=16 performs on par with full fine-tuning while using roughly 200 times fewer parameters. Analysis of the labeled corpus—in which (with negative reviews intentionally oversampled for training and therefore do not represent population proportions—) shows FOOD as the most frequently mentioned aspect (64.4% of reviews), while SERVICE and PRICE carry the largest share of complaints (around 36% each), and FOOD and PLACE remain dominated by positive sentiment. This study confirms LoRA as an efficient alternative for Indonesian ABSA while producing managerial recommendations based on complaint themes for Soramen.
Pengembangan Sistem Automation Feedback Berbasis Gemini Sebagai Pendukung Problem-Based Learning Sifa Fauzan; Eki Nugraha; Yuli Sopianti
Journal of Information Technology Vol. 6 No. 2 (2026): Journal of Information Technology
Publisher : Institut Shanti Bhuana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46229/jifotech.v6i2.1152

Abstract

A preliminary observation of 31 eleventh-grade students in the Network and Application Engineering (SIJA) program at a vocational school in Cimahi found that all students (100%) had come to rely on generative AI such as ChatGPT whenever they encountered coding difficulties, with 86.7% reporting an inability to complete programming tasks independently without AI assistance. This AI dependency risks hindering the development of students' critical reasoning. This research aims to design, implement, and test an automated feedback system named AutoFeed to support the Problem-Based Learning (PBL) model in mitigating AI dependency while enhancing students' critical thinking skills in Informatics subjects at vocational high schools (SMK). The research methodology applies the Waterfall development model, encompassing requirements analysis, system design, software implementation, and testing phases. The application was built using a technology architecture consisting of React on the frontend, FastAPI (Python) on the backend, and MySQL as the database, integrating the Google Gemini 2.5 Flash model as the processing engine for hybrid (corrective and reflective) feedback through Socratic questioning techniques. The results of expert judgment based on LORI standards showed an average usability score of 4.60, workspace-PBL feature alignment scored 4.25, while the validation of AI pedagogical response accuracy scored 4.00. Functional testing further confirmed that all system features operated as intended but still require refinement. Thus, the AutoFeed system is confirmed feasible as a digital learning assistant (co-thinker), designed to minimize delayed feedback constraints and support students' critical reasoning, with its actual learning impact recommended for further empirical validation.

Page 9 of 9 | Total Record : 86

 5   6   7   8   9 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol. 6 No. 2 (2026): Journal of Information Technology Vol. 6 No. 1 (2026): Journal of Information Technology Vol 5 No 1 (2025): Journal of Information Technology Vol 4 No 2 (2024): Journal of Information Technology Vol 4 No 1 (2024): Journal of Information Technology Vol 3 No 2 (2023): Journal of information Technology Vol 3 No 1 (2023): Journal of Information Technology Vol 2 No 2 (2022): Journal of information Technology Vol 2 No 1 (2022): Journal of information Technology Vol 1 No 2 (2021): Journal of Information Technology Vol 1 No 1 (2021): Journal of Information Technology More Issue