ipsikom

PENGARUH PENGGUNAAN APLIKASI BACAAN DIGITAL TERHADAP MINAT BACA SISWA MENENGAH PERTAMA (SMP)

2025-07-02T07:17:10+00:00

Penelitian ini bertujuan untuk mengetahui pengaruh penggunaan aplikasi bacaan digital terhadap minat baca siswa Sekolah Menengah Pertama (SMP) di Kabupaten Bulukumba. Penelitian ini menggunakan pendekatan kuantitatif deskriptif dengan teknik pengumpulan data melalui kuesioner. Data dianalisis menggunakan perhitungan rata-rata dan persentase terhadap indikator minat baca yang meliputi frekuensi membaca, durasi membaca, dan ketertarikan terhadap konten. Hasil penelitian menunjukkan bahwa sebagian besar siswa telah menggunakan aplikasi bacaan digital seperti iPusnas, Let’s Read, dan e-Perpus. Responden memberikan tanggapan positif terhadap kemudahan akses, keberagaman konten, dan fitur interaktif dari aplikasi tersebut. Skor tertinggi terdapat pada indikator ketertarikan terhadap konten, diikuti oleh frekuensi dan durasi membaca. Tingginya persentase siswa yang menyatakan setuju dan sangat setuju menunjukkan bahwa aplikasi bacaan digital memberikan kontribusi positif terhadap kebiasaan membaca mereka. Implikasinya, aplikasi bacaan digital dapat menjadi media literasi yang efektif dalam mendorong minat baca siswa, kususunya di Kabupaten Bulukumba. Sekolah dapat memanfaatkan aplikasi ini sebagai alternatif pembelajaran yang sesuai dengan karakteristik generasi digital. Penelitian ini diharapkan menjadi referensi dalam pengembangan program literasi berbasis teknologi secara berkelanjutan.

SENTIMENT ANALYSIS OF THE MERDEKA CURRICULUM USING VADER AND LSTM

2025-07-18T07:58:12+00:00

This study explores public sentiment toward the Merdeka Curriculum, a policy reform introduced to address educational challenges in Indonesia following the COVID-19 pandemic. Utilizing Twitter (now X) as a data source, this research collected 1,900 Indonesian-language tweets to assess how society perceives the curriculum’s flexibility and relevance. The analysis begins with data preprocessing, including cleaning, tokenization, stopword removal, and stemming. VADER (Valence Aware Dictionary and Sentiment Reasoner) is employed for initial sentiment labeling, classifying tweets into positive, neutral, and negative categories. The results reveal a significant class imbalance: 1,692 neutral, 117 positive, and 91 negative tweets. These labeled tweets are further analyzed using the Long Short-Term Memory (LSTM) algorithm for deep sentiment classification. The LSTM model demonstrates training accuracy improvements from 82% to 90.29% across five epochs, while validation accuracy remains steady at 88%. However, the model fails to accurately classify minority classes, with precision, recall, and F1-scores for positive and negative sentiments scoring zero. This indicates that while LSTM can effectively recognize the dominant neutral sentiment, it struggles with minority class identification due to data imbalance. The findings highlight the need for improved model training strategies and data augmentation to enhance classification performance across all sentiment categories. Overall, this study contributes to the integration of lexicon-based and deep learning approaches for sentiment analysis and offers valuable insights for educators and policymakers in optimizing the Merdeka Curriculum through data-informed decisions.

ANALISIS SENTIMEN MASYARAKAT TERHADAP PINJAMAN ONLINE DI APLIKASI X MENGGUNAKAN LONG SHORT-TERM MEMORY

2025-07-18T03:26:21+00:00

The development of online loans in Indonesia has led to various public opinions spread across social media, one of which is the X platform. This research aims to analyze public sentiment towards online loans using the Long Short-Term Memory (LSTM) method. The data used consists of 702 Indonesian tweets collected through a crawling process with Tweet Harvest. Of these, 480 tweets were classified as positive sentiment and 222 as negative. The research process includes preprocessing, manual labeling, model training, and evaluation stages. The model was built using Sequential architecture from Keras, consisting of embedding layer, LSTM layer 128 units, 30% dropout, and output layer with softmax activation function. The model was trained using 562 tweets as training data and 140 tweets as validation data with a ratio of 80:20, for 10 epochs and batch size 64. The final evaluation using the entire dataset resulted in 92.59% accuracy, with 79.06% precision, 79.43% recall, and 79.14% F1-score. These results show that LSTM is able to classify sentiment stably and effectively, and has strong potential in sentiment analysis on short text data such as tweets.

APLIKASI PERMAINAN KARTU MEMORI BERBASIS WEB UNTUK PEMBELAJARAN KOSAKATA BAHASA SUNDA (STUDI KASUS SEKOLAH DASAR NEGERI BINAWARGA CIPONGKOR)

2025-07-23T06:00:59+00:00

In today's digital era, technology-based learning is an important need, especially in maintaining the use of regional languages such as Sundanese which are increasingly rarely used in everyday life. This study aims to design, implement, and test a web-based memory card game application as a medium for learning Sundanese vocabulary for elementary school students. The development method used is the waterfall model which includes the stages of analysis, design, implementation, testing, deployment, and maintenance. This application was developed using React with Tailwind CSS for the frontend, Node.js with Express JS, and PostgreSQL as the database. The main features provided include difficulty level selection, point system, leaderboard, and vocabulary and student data management by the admin. The results of black box testing all features have run 100% according to their functions, and the results of User Acceptance Testing (UAT) from 3 testing parameters namely features, design, and user satisfaction show a very positive response from teachers with a satisfaction level of 95.1% and from students of 74.6%. These findings show that the application can be well received by users and is able to increase students' interest in learning Sundanese language.

SISTEM ENKRIPSI FILE DENGAN ID-CARD MENGGUNAKAN LARAVEL

2025-08-20T02:30:34+00:00

The security of digital data has become crucial in today's era of information exchange. Many data breaches occur due to weak file protection in web-based systems. This research aims to design and develop a web-based file encryption system using the Advanced Encryption Standard (AES) algorithm, where file access is restricted only to users who possess a valid ID Card or QR Code as an authentication key. The software development approach adopted in this development is the Waterfall methodology, which follows a sequential process consisting of requirement analysis, system design, implementation, and testing phases. The software was built using the Laravel framework with key features such as automatic file encryption upon upload, folder management, and additional authentication through ID Card or QR Code scanning. Administrator has full access to manage users while regular users can only upload and manage their private files. The implementation result show that files were successfully encrypted and can only be accessed using a valid ID Card. The AES encryption process effectively secures file confidentiality, while the use of an ID Card enhances access security to the uploaded files. Therefore, this software can fulfills the research objective of improving file security in web-based systems.

APLIKASI PENINGKATAN KEMAMPUAN MEMBACA BERBASIS MULTIMEDIA INTERAKTIF MENGGUNAKAN CONSTRUCT 2 (STUDI KASUS SDN SINARJAYA)

2025-07-26T09:14:47+00:00

Pendidikan memiliki peran penting dalam mengembangkan potensi individu dan mempersiapkan keterampilan berbahasa terutama membaca menjadi fondasi utama dalam proses belajar, khususnya bagi siswa Sekolah Dasar (SD). Berdasarkan observasi awal di SDN Sinarjaya, ditemukan bahwa sebagian besar siswa kelas 2 masih mengalami kesulitan dalam membaca dengan lancar. Penelitian ini bertujuan untuk merancang dan membuat aplikasi pembelajaran membaca berbasis multimedia interaktif menggunakan Construct 2. Aplikasi dirancang dengan fitur menarik seperti merangkai kata, komik digital dan fitur tambahan berupa suara dan kuis. Metode yang digunakan dalam pembuatan aplikasi game sederhana ini adalah MDLC (Multimedia Development Life Cycle) dengan 6 tahap yaitu konsep, perancangan, pengumpulan, pembuatan, testing dan pendistribusian. Hasil pembuatan aplikasi game ini menggunakan Construct 2, dimana tahap kegiatan sesuai dengan metode yang digunakan. Diharapkan aplikasi game berbasis multimedia interaktif ini dapat berkontribusi secara signifikan dalam menciptakan pembelajaran yang lebih baik dan relevan dengan kebutuhan siswa Sekolah Dasar era digital.

Membaca, Pembelajaran, MDLC, Construct 2

APLIKASI PELAPORAN BULLYING (DUCARE) BERBASIS WEB (STUDI KASUS DARUL ‘ULUM CIWIDEY-PASIRJAMBU)

2025-07-30T07:16:37+00:00

Bullying di lingkungan sekolah menjadi isu serius yang memerlukan penanganan cepat dan tepat. Penelitian ini merancang dan membangun aplikasi pelaporan bullying berbasis web bernama DUCARE yang diterapkan di Darul 'Ulum Ciwidey-Pasirjambu. Aplikasi ini memfasilitasi pelapor untuk menyampaikan laporan bullying secara anonim maupun non-anonim, serta mendukung tiga peran pengguna yaitu pelapor, guru BK, dan admin. Fitur-fitur utama meliputi form pelaporan, manajemen laporan, notifikasi, dan pelacakan status penanganan. Berdasarkan pengujian fungsional (Black Box) dan User Acceptance Test (UAT) dengan 15 responden, aplikasi memperoleh tingkat kepuasan sebesar 88,7%, yang menunjukkan bahwa aplikasi ini layak digunakan dan membantu meningkatkan efektivitas penanganan kasus bullying secara digital di lingkungan sekolah.

RANCANG BANGUN APLIKASI ANALISIS SENTIMEN ULASAN APLIKASI DI GOOGLE PLAY STORE MENGGUNAKAN METODE LOGISTIC REGRESSION DAN LEXICON-BASED APPROACH

2025-08-21T02:35:43+00:00

In the increasingly advanced digital era, user reviews of mobile applications on platforms such as the Google Play Store have become an important source of information for both developers and users. These reviews can reflect user satisfaction, complaints, and expectations for an application. However, due to the ever-increasing volume of reviews, it is very difficult for developers to read and evaluate all opinions manually. On the other hand, available reviews often do not reflect the actual conditions due to the presence of fake, biased, or manipulative reviews. Therefore, an automated system is needed that can accurately group reviews based on sentiment polarity. This study aims to design and build a web-based application using the Streamlit framework that can perform sentiment analysis on application reviews on the Google Play Store. The method used is a combination of Logistic Regression and Lexicon-Based Approach with text preprocessing stages such as cleansing, tokenizing, stemming, and transformation using TF-IDF. This study uses the CRISP-DM approach in building the application model and system. As part of the system design, a prototype model was created in the form of a use case diagram, use case scenario, and activity diagram to describe the functional requirements and the flow of user interaction with the system. The final result of this research is a sentiment analysis application capable of classifying reviews into positive and negative categories, as well as displaying the model evaluation results in the form of metric visualizations and word clouds. From the Dana application case study, based on the results of the model performance evaluation using the confusion matrix metric, the Logistic Regression model built achieved an accuracy of 91.2%, a precision of 91.73%, a recall of 98.46%, and an F1-score of 64.78%.

IMPLEMENTASI CONVOLUTIONAL NEURAL NETWORK (CNN) UN-TUK KLASIFIKASI TANAMAN HIAS BERBASIS APLIKASI WEB LARAVEL

2025-07-26T09:10:24+00:00

The automatic classification of ornamental plants plays a vital role in improving efficiency in garden management and digital agriculture. This study aims to develop an image-based ornamental plant classification system using the Convolutional Neural Network (CNN) method, integrated into a Laravel-based web application. The CNN model was trained on a dataset comprising over 14,000 images from 29 ornamental plant classes. Data augmentation techniques were applied to enhance the model’s generalization ability. The research process involved image preprocessing, CNN model training, performance evaluation using accuracy, precision, recall, and F1-score, and system deployment through a web interface developed with Laravel. The training results showed a validation accuracy of 77.38%. The deployed system is capable of real-time prediction based on user-uploaded plant images. In one of the tests, a rose image yielded a classification accuracy of 56%, indicating varying performance depending on plant class. These results suggest that integrating CNN with a Laravel-based web platform can provide a reliable tool for classifying ornamental plants. The system demonstrates potential use in household plant identification, gardening support, and plant education. Further improvements may include expanding the dataset, refining class balance, and optimizing model architecture to increase accuracy for specific plant types.

PERANCANGAN FITUR ANOTASI PADA CHATGPT MENGGUNAKAN EKSTENSI BROWSER

2025-07-28T10:02:16+00:00

The rapid advancement of large language models such as ChatGPT has revolutionized text-based interactions, yet lacks built-in annotation mechanisms for marking, storing, and revisiting critical conversation points. This study designs and implements a browser extension using ReactJS and Tailwind CSS with local storage via IndexedDB, following a five-stage waterfall model encompassing requirements analysis, system design, implementation, testing (black-box and user acceptance), and maintenance. The extension supports CRUD operations on annotations, automatic navigation to annotated text positions, and JSON import/export without disrupting ChatGPT’s original interface. Testing demonstrates full compliance with functional specifications, while a UAT with 11 participants reports average satisfaction scores ≥ 4.55 for usability, UI coherence, and review efficiency, confirming enhanced productivity and learning experience. In conclusion, the extension effectively facilitates critical thinking and collaboration in web-based learning, with future work exploring cross-device synchronization, real-time collaboration, and AI-driven annotation suggestions to further optimize user engagement.

ANALISIS PEMAHAMAN GURU DAN SISWA TERHADAP PEMBELAJARAN DARING DI SDN 199 TANAH KONGKONG

2025-08-21T02:43:46+00:00

Pandemi COVID-19 telah memaksa seluruh satuan pendidikan, termasuk sekolah dasar, untuk melaksanakan pembelajaran daring. Perubahan ini menjadi tantangan bagi guru dan siswa, khususnya di daerah dengan keterbatasan infrastruktur teknologi. Penelitian ini bertujuan untuk menganalisis tingkat pemahaman guru dan siswa terhadap pelaksanaan pembelajaran daring di SDN 199 Tanah Kongkong. Metode yang digunakan adalah deskriptif kuantitatif dengan teknik pengumpulan data melalui angket skala Likert dan wawancara sebagai data pendukung. Subjek penelitian adalah guru kelas dan siswa kelas tinggi. Hasil penelitian menunjukkan bahwa pemahaman guru terhadap pembelajaran daring masih beragam; sebagian guru memahami konsep dan teknis pelaksanaannya dengan baik, namun sebagian lainnya masih mengalami kesulitan dalam penguasaan teknologi. Di sisi siswa, ditemukan bahwa sebagian besar memahami tujuan pembelajaran daring, tetapi masih mengalami kendala dalam akses internet dan penggunaan perangkat. Penelitian ini merekomendasikan adanya pelatihan teknologi untuk guru dan pendampingan intensif bagi siswa guna meningkatkan efektivitas pembelajaran daring.

PENERAPAN DATA WAREHOUSE PADA ELEKTRONIK SURAT PEMBERITAHUAN PAJAK DAERAH (E-SPTPD)

2025-07-24T09:43:04+00:00

Penggunaan data warehouse telah banyak menghasilkan banyak keuntungan bagi organisasi, termasuk dalam melakukan analisa data dan penghematan waktu yang lebih baik oleh pengguna. Proses membangun data warehouse dengan metode sembilan langkah Kimball pada aplikasi Elektronik Surat Pemberitahuan Pajak Daerah (E-SPTPD) di Kota Tangerang telah memberikan banyak manfaat bagi organisasi, termasuk dalam melakukan analisa data dan efisiensi waktu. Karena meningkatnya kompleksitas data dalam pengelolaan, data warehouse kini banyak diminati oleh pengguna aplikasi di dunia bisnis dan organisasi. Penelitian ini bertujuan untuk mengevaluasi efektivitas penerapan sistem data warehouse menggunakan aplikasi Pentaho dalam menyajikan laporan pendapatan pajak daerah pada Bidang Pendapatan Lainnya. Evaluasi dilakukan melalui perbandingan waktu antara proses manual dengan sistem OLAP, Report Designer, dan Dashboard. Hasil menunjukkan bahwa sistem secara signifikan mempercepat proses penyajian laporan, dengan rata-rata waktu 3,80 detik untuk OLAP, 1,77 detik untuk Report Designer, dan 1,64 detik untuk Dashboard, dibandingkan proses manual yang membutuhkan lebih dari 1.200 detik. Evaluasi juga mencakup persepsi pengguna terhadap sistem melalui kuesioner berbasis Technology Acceptance Model (TAM). Lima responden yang terdiri dari pejabat dan staf menunjukkan respons positif dengan nilai rata-rata persepsi manfaat 4,36, kemudahan penggunaan 4,20, sikap pengguna 4,27, dan intensi perilaku 4,20 dari skala Likert 1–5. Hasil ini mengindikasikan bahwa penerapan data warehouse meningkatkan efektivitas, efisiensi, dan kepuasan pengguna dalam pengelolaan data dan pelaporan pendapatan pajak daerah. Sistem ini dinilai mampu mendukung pengambilan keputusan yang lebih cepat dan tepat di lingkungan pemerintahan.

PENGARUH INTENSITAS PENGGUNAAN TIKTOK TERHADAP TINGKAT KECEMASAN SOSIAL PADA REMAJA USIA 15-18 TAHUN

2025-06-23T02:08:45+00:00

Kemajuan teknologi dan kehadiran platform sosial seperti TikTok telah memberikan pengaruh besar terhadap aspek sosial dan psikologis remaja. Penggunaan TikTok secara berlebihan terbukti dapat meningkatkan tekanan sosial dan memicu kecemasan, khususnya pada kalangan remaja. Penelitian ini difokuskan untuk mengevaluasi dampak intensitas penggunaan TikTok terhadap tingkat kecemasan sosial pada remaja usia 15 hingga 18 tahun di Kota Bulukumba. Metode yang digunakan adalah pendekatan kuantitatif, dengan menilai frekuensi dan durasi penggunaan TikTok serta mengukur tingkat kecemasan sosial melalui kuesioner. Hasil penelitian menunjukkan bahwa 61,83% responden mengalami kecemasan sosial dalam kategori sedang hingga tinggi, yang mengindikasikan adanya korelasi antara tingginya aktivitas di TikTok dengan gejala kecemasan sosial. Temuan ini menjadi dasar penting dalam merancang strategi penggunaan media sosial yang lebih sehat dan seimbang bagi remaja.

PENGARUH KECANDUAN GAME ONLINE TERHADAP PRESTASI BELAJAR ANAK USIA SEKOLAH DASAR

2025-07-03T03:00:02+00:00

Penelitian ini bertujuan untuk mengetahui pengaruh kecanduan game online terhadap prestasi belajar siswa sekolah dasar. Fokus penelitian ini adalah siswa kelas IV dan V di SD Negeri 56 Balandidi, Kabupaten Bulukumba, dengan jumlah responden sebanyak 20 orang. Pendekatan yang digunakan adalah kuantitatif deskriptif dengan teknik pengumpulan data berupa kuesioner dan dokumentasi nilai rapor. Instrumen penelitian disusun dalam bentuk angket tertutup berbasis skala Likert 5 poin, yang mencakup tiga indikator utama: frekuensi bermain game online, dampak terhadap belajar, dan manajemen waktu serta tanggung jawab belajar.Hasil penelitian menunjukkan bahwa frekuensi bermain game online siswa cukup tinggi, dengan persentase 78%. Dampak terhadap prestasi belajar tercatat sebesar 73,7%, yang menunjukkan adanya pengaruh negatif meskipun tidak signifikan pada semua responden. Di sisi lain, indikator manajemen waktu memperoleh skor 75,3%, yang menandakan bahwa sebagian siswa masih mampu membagi waktu antara bermain dan belajar. Rata-rata skor keseluruhan dari ketiga indikator adalah 78%, yang mencerminkan bahwa penggunaan game online telah menjadi bagian dari keseharian siswa dan memiliki dampak terhadap kebiasaan belajar mereka.Dapat disimpulkan bahwa meskipun game online memberikan hiburan, penggunaannya yang berlebihan dapat berdampak pada prestasi akademik. Oleh karena itu, diperlukan pengawasan dan peran aktif dari guru maupun orang tua dalam membimbing siswa agar lebih bijak dalam menggunakan teknologi.

SISTEM INFORMASI PENGUPAHAN PADA TERNAMA KONVEKSI BERBASIS WEB

2025-07-05T03:05:00+00:00

This study aims to analyze, design, implement and test the wage information system at Ternama Konveksi based on WEB. In this study the author obtained data by conducting observations, interviews and literature studies. The development carried out to overcome these problems is using the waterfall method and PIECES analysis by finding weaknesses in the running system. This wage information system is designed using a programming language with HTML (Hypertext Markup Language) database software, PhpMyAdmin, MySQL, XAMPP, Visual Studio Code, then tested with black box testing. In data processing, users only input data into the system then data processing will be carried out by the system until the creation of wage reports and employee pay slips. The results of the wage information system test have fulfilled its function according to the proposed design and can be a solution related to the wage information system at Ternama Konveksi in the process of calculating and paying employee wages.

SISTEM INFORMASI PEMBELIAN DAN PENJUALAN PADA TERNAMA KONVEKSI BERBASIS WEB

2025-07-09T02:17:39+00:00

Ternama Konveksi still uses spreadsheets to record sales and purchase transactions, which leads to data entry errors, duplication, and delays in reporting. This study aims to address these issues by designing a web-based Sales and Purchase Information System using the waterfall method. The system improves transaction data entry speed, minimizes human errors, and stores data in a structured database. User Acceptance Testing (UAT) results show a user satisfaction rate of 90,89%, categorized as “Excellent.”

DETEKSI KESEGARAN IKAN BANDENG DENGAN ALGORITMA CONVOLUTIONAL NEURAL NETWORK (CNN)

2025-07-19T02:12:12+00:00

Fish freshness is a key indicator in ensuring food quality and safety, especially in milkfish (Chanos chanos) which is widely consumed in Indonesia. Manual freshness assessment is subjective and requires special skills, so an accurate automated approach is needed. This study aims to develop a digital image-based milkfish freshness classification application using the Convolutional Neural Network (CNN) method with a transfer learning approach. The dataset used consists of 445 milkfish images in two classes: fresh and not fresh, with an augmentation process to enrich the visual variety. Two models were compared: Model A (baseline) and Model B (enhancement with Dropout and fine-tuning). The evaluation results show that Model A has 33% accuracy, 50% precision, and 50% recall, In contrast, Model B has 67% accuracy, 50% precision, and 100% recall, showing more stable prediction in Streamlit-based applications. These findings suggest that the integration of CNN and transfer learning can be effectively applied to support the digitization of fish-based food product quality. Further development is suggested through the addition of training data, multi-class classification, and integration to mobile or IoT devices.