cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Bahar
Contact Email
bahararahman@gmail.com
Phone
-
Journal Mail Official
puslit.stmikbjb@gmail.com
Editorial Address
-
Location
Kota banjarmasin,
Kalimantan selatan
INDONESIA
Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi
Published by Sekolah Tinggi Manajemen Informatika dan Komputer Banjarbaru
ISSN : 20893787     EISSN : 26850893     DOI : -
Core Subject : Science,
Computer Science & IT
Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi adalah Jurnal Ilmiah bidang Teknik Informatika dan Sistem Informasi yang diterbitkan secara periodik tiga nomor dalam satu tahun, yaitu pada bulan April, Agustus dan Desember. Redaksi Jutisi: Jurnal Ilmiah Teknik Informatika dan Sistem Informasi menerima sumbangan tulisan hasil penelitian atau atau artikel konseptual bidang Teknik Informatika dan Sistem Informasi.
Arjuna Subject : -
Articles 1,128 Documents
 109   110   111   112   113 
Analisis Sentimen dan Distorsi Kognitif Konflik Anggaran Pendidikan dengan Makan Bergizi Gratis Azzrial Arfiansyah; Cinta Auliya Kusuma Ananda; Quyun Isnawan
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol. 15 No. 4 (2026): Agustus 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i4.3924

Abstract

The budget allocation conflict of the Free Nutritious Meal (MBG) program amounting to Rp223.5 trillion within the 2026 education budget has triggered opinion polarization and collective thinking bias on social media X. This study aims to analyze public sentiment distribution, identify dominant cognitive distortions, and test the statistical correlation between them. The methodology employs a two-layer parallel NLP pipeline utilizing the IndoBERTweet model for sentiment classification and the IndoBERT-base model for multilabel cognitive distortion detection across 2,000 tweets. Evaluation results show that the sentiment model achieves 83.25% accuracy, while the cognitive distortion detection reaches a subset accuracy of 83.75%, with Mental Filter being the most dominant type (8.2%). Fisher's Exact test proves a significant association (  < 0.05) between negative sentiment and the occurrence of Mental Filter and Catastrophizing. In conclusion, this hybrid approach effectively maps public collective thinking biases toward public policy dynamics. Keywords: Sentiment Analysis; Cognitive Distortion; Free Nutritious Meal; IndoBERTweet; Fleiss' Kappa Abstrak Konflik alokasi anggaran program Makan Bergizi Gratis (MBG) sebesar Rp223,5 triliun dalam anggaran pendidikan APBN 2026 memicu polarisasi opini dan bias berpikir kolektif di media sosial X. Penelitian ini bertujuan menganalisis distribusi sentimen publik, mengidentifikasi distorsi kognitif dominan, serta menguji korelasi statistik di antara keduanya. Metodologi yang digunakan adalah pipeline NLP dua lapis paralel berbasis model IndoBERTweet untuk klasifikasi sentimen dan IndoBERT-base untuk deteksi distorsi kognitif multi-label terhadap 2.000 tweet. Hasil evaluasi menunjukkan model sentimen mencapai akurasi 83,25%, sedangkan deteksi distorsi kognitif meraih subset accuracy 83,75% dengan Mental Filter sebagai tipe paling dominan (8,2%). Uji Fisher's Exact membuktikan adanya hubungan signifikan (  < 0,05) antara sentimen negatif dengan kemunculan distorsi kognitif Mental Filter dan Catastrophizing. Simpulannya, pendekatan hybrid ini efektif dalam memetakan bias berpikir kolektif masyarakat terhadap dinamika kebijakan publik. Kata Kunci: Analisis Sentimen; Distorsi Kognitif; Makan Bergizi Gratis; IndoBERTweet; Fleiss' Kappa
Pengembangan Sistem Pembayaran Digital Berbasis Virtual Account dan Tracer Digital untuk Meningkatkan Efisiensi Layanan Keuangan Perguruan Tinggi Virjayanti Lazinu Jamal; Lidya Aprilia Jumroh; Musriani Musriani; M. Indra Maulana
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol. 15 No. 4 (2026): Agustus 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i4.3956

Abstract

Student payment services require a system that can support transactions and payment status monitoring in an integrated manner. This study aims to develop a digital payment system based on Virtual Account and Digital Tracer to support student payment services at Universitas Pendidikan Muhammadiyah Sorong. The research employed a Research and Development (R&D) method consisting of needs analysis, system design, implementation, and system testing. The system was tested using Black Box Testing and User Acceptance Testing (UAT). The functional testing results showed that all tested system functions operated successfully. Expert validation obtained scores of 3.80 for software, 3.67 for effectiveness, and 3.40 for practicality. User evaluation indicated that the system could support student payment processes and transaction monitoring. Therefore, the developed system can be used to support more integrated and accessible student payment services. Keywords: Digital Payment System; Virtual Account; Digital Tracer; Black Box Testing; User Acceptance Testing. Abstrak Proses pembayaran mahasiswa memerlukan sistem yang mampu mendukung transaksi dan pemantauan status pembayaran secara terintegrasi. Penelitian ini bertujuan mengembangkan sistem pembayaran digital berbasis Virtual Account dan Tracer Digital untuk mendukung layanan pembayaran mahasiswa di Universitas Pendidikan Muhammadiyah Sorong. Metode penelitian menggunakan Research and Development (R&D) dengan tahapan analisis kebutuhan, perancangan, implementasi, dan pengujian sistem. Pengujian dilakukan menggunakan Black Box Testing dan User Acceptance Testing (UAT). Hasil pengujian fungsional menunjukkan seluruh fungsi sistem berhasil dijalankan. Validasi ahli memperoleh skor aspek perangkat lunak 3,80, efektivitas 3,67, dan kepraktisan 3,40. Hasil evaluasi pengguna menunjukkan sistem dapat mendukung proses pembayaran dan pemantauan transaksi mahasiswa. Dengan demikian, sistem yang dikembangkan dapat digunakan sebagai pendukung layanan pembayaran mahasiswa yang lebih terintegrasi dan mudah digunakan. Kata kunci: Sistem Pembayaran Digital; Virtual Account; Tracer Digital; Black Box Testing; User Acceptance Testing.
Analisis Sentimen Evaluasi Pembelajaran Udemy Menggunakan Support Vector Machine Untuk Peningkatan Kursus Irwansyah Irwansyah; Ellya Helmud
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol. 15 No. 4 (2026): Agustus 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i4.3968

Abstract

Learning evaluation plays an important role in improving course quality, yet user reviews are generally unstructured and difficult to analyze manually. This study aims to analyze user sentiment toward Udemy course evaluations using the Support Vector Machine (SVM) algorithm. The dataset consisted of 50 balanced English-language reviews (26 positive and 24 negative) selected from approximately 500 scraped reviews, with sentiment labels determined based on the rating categories provided by the source website. The research process included text preprocessing, TF-IDF feature weighting, SVM classification using a linear kernel, and 10-fold cross-validation. Model performance was evaluated using accuracy, precision, recall, and F1-score. The proposed model achieved an accuracy of 82% and an average F1-score of 0.82, indicating that the combination of TF-IDF and SVM effectively classifies user sentiment. These findings can assist course providers in evaluating user feedback and improving learning quality. Keywords: Sentiment Analysis; Support Vector Machine; TF-IDF; Business Intelligence; Learning Evaluation Abstrak Evaluasi pembelajaran berperan penting dalam meningkatkan kualitas kursus, namun ulasan pengguna umumnya berupa data teks tidak terstruktur yang sulit dianalisis secara manual. Penelitian ini bertujuan menganalisis sentimen pengguna terhadap evaluasi pembelajaran pada platform Udemy menggunakan algoritma Support Vector Machine (SVM). Dataset terdiri atas 50 ulasan berbahasa Inggris yang seimbang (26 positif dan 24 negatif) dari sekitar 500 hasil scraping, dengan label sentimen ditentukan berdasarkan kategori rating pada situs sumber. Tahapan penelitian meliputi preprocessing teks, pembobotan TF-IDF, klasifikasi SVM berkernel linear, dan validasi menggunakan 10-fold cross validation. Kinerja model dievaluasi menggunakan accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan accuracy sebesar 82% dan rata-rata F1-score sebesar 0,82, sehingga kombinasi TF-IDF dan SVM efektif mengklasifikasikan sentimen pengguna serta dapat mendukung peningkatan kualitas pembelajaran. Kata Kunci: Analisis Sentimen; Support Vector Machine; TF-IDF; Business Intelligence; Evaluasi Pembelajaran
A Hybrid Scoring and Machine Learning Framework for Quantitative Modeling of Customer Payment Potential Cindy Kristiya Himawan; Kevin Sebastian Brilian; Ivan Michael Siregar
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol. 15 No. 4 (2026): Agustus 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i4.3534

Abstract

Debt collection generates extensive interaction data collection actions, contact outcomes, and communication history that is traditionally recorded only qualitatively for documentation, limiting its analytical value. This study aims to develop a scoring-based framework that converts qualitative collection data into quantitative indicators for data-driven decision-making. The method begins with a rule-based scoring mechanism to encode collection actions and interaction history into a total score reflecting customer payment potential, then extends this baseline using machine learning to learn feature importance and improve prediction accuracy. Model performance is evaluated using AUC ROC and Precision@K for payment likelihood, MAE and RMSE for payment time prediction, and recovery rate for business impact. Results show that the hybrid model significantly improves prioritization efficiency and recovery outcomes compared to conventional qualitative methods, demonstrating how operational data can be systematically quantified and integrated with predictive analytics for smarter collection strategies.
Sistem Pendukung Keputusan untuk Penilaian Kesehatan Keuangan UMKM Menggunakan Metode Pembobotan Skor Rendy Muhamad Dezan Rachdiansyah Hamdani; Dinar Rahayu
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol. 15 No. 4 (2026): Agustus 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i4.3650

Abstract

Abstract Micro, Small, and Medium Enterprises (MSMEs) play a strategic role in the national economy; however, limited digital financial literacy and difficulty converting transaction records into strategic insight remain major challenges to business sustainability. This study aims to design and evaluate an intelligent decision support system called SME Guardian AI to automatically assess the financial health of business owners. The system was developed through a phased systems development life cycle approach, integrating a score-weighting method across three key financial indicators: net profit margin, break-even point status, and profit growth trend. The system was successfully implemented as an interactive dashboard that classifies business conditions into three risk levels on a score range of zero to one hundred. Functional testing showed that all system modules operated reliably with a full success rate. An accuracy-validation protocol based on a confusion matrix was also designed and demonstrated using hypothetical data. These findings confirm that the developed system provides a systematic analytical framework for business owners to convert raw data into strategic recommendations. Keyword: Decision Support System; Financial Health; Micro Small and Medium Enterprises; Score Weighting; Analytical Dashboard; Confusion Matrix.   Abstrak Usaha Mikro, Kecil, dan Menengah berperan strategis dalam perekonomian nasional, namun keterbatasan literasi keuangan digital dan kesulitan mengonversi catatan transaksi menjadi wawasan strategis masih menjadi tantangan utama keberlanjutan usaha. Penelitian ini bertujuan merancang dan mengevaluasi sistem pendukung keputusan cerdas bernama SME Guardian AI untuk menilai kesehatan finansial pelaku usaha secara otomatis. Sistem dikembangkan melalui pendekatan siklus hidup pengembangan sistem bertahap, mengintegrasikan metode pembobotan skor pada tiga indikator finansial utama, yaitu margin laba bersih, status titik impas usaha, dan tren pertumbuhan laba. Sistem berhasil diimplementasikan sebagai dasbor interaktif yang mengklasifikasikan kondisi bisnis ke dalam tiga tingkat risiko dengan rentang skor nol hingga seratus. Pengujian fungsional menunjukkan seluruh modul sistem beroperasi reliabel dengan tingkat keberhasilan penuh. Sebuah protokol validasi akurasi berbasis matriks kebingungan turut dirancang dan didemonstrasikan menggunakan data hipotetis. Temuan ini menegaskan sistem yang dikembangkan menyediakan kerangka kerja analitis sistematis bagi pelaku usaha mengonversi data mentah menjadi rekomendasi strategis.
Analisis Literasi Digital dan Trust Gen Z terhadap Niat Membagikan Deepfake berdasarkan Model TPB Afrina Layanti Pasaribu; Rizqa Raaiqa Bintana; Hasanatul Iftitah
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol. 15 No. 3 (2026): Juni 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i3.3687

Abstract

Abstract This study aimed to analyze the factors influencing Generation Z’s intention to share deepfake content on social media. The problem addressed was the increasing spread of deepfake content that may cause negative impacts. This study used a quantitative approach with a survey method through questionnaires distributed to 106 respondents in Jambi Province. Data were analyzed using Structural Equation Modeling based on Partial Least Squares. The results showed that Subjective Norm and Perceived Behavioral Control significantly influenced intention, while Attitude, digital literacy, and trust did not have a significant effect. These findings indicated that user behavior was more influenced by social factors and system ease of use rather than individual factors. This study contributed to understanding user behavior and provided implications for the development of more responsible digital systems. Keywords: Deepfake; Theory of Planned Behavior; Generation Z; Digital Literacy; Trust   Abstrak Penelitian ini bertujuan untuk menganalisis faktor-faktor yang memengaruhi niat generasi Z dalam membagikan konten deepfake di media sosial. Permasalahan yang diangkat adalah meningkatnya penyebaran konten deepfake yang berpotensi menimbulkan dampak negatif. Penelitian ini menggunakan pendekatan kuantitatif dengan metode survei melalui kuesioner kepada 106 responden di Provinsi Jambi. Analisis data dilakukan menggunakan Structural Equation Modeling berbasis Partial Least Squares. Hasil penelitian menunjukkan bahwa Subjective Norm dan Perceived Behavioral Control berpengaruh signifikan terhadap intention, sedangkan Attitude, Literasi Digital, dan Truts tidak berpengaruh signifikan. Temuan ini menunjukkan bahwa perilaku pengguna lebih dipengaruhi oleh faktor sosial dan kemudahan sistem dibandingkan faktor individu. Penelitian ini memberikan kontribusi dalam memahami perilaku pengguna serta implikasi bagi pengembangan sistem digital yang lebih bertanggung jawab.
Klasifikasi Jenis Sampah Menggunakan Transfer Learning Berbasis EfficientNetV2-B0 dengan Strategi Fine-Tuning Jose Farrel Samgar; Nur Rachmat
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol. 15 No. 4 (2026): Agustus 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i4.3773

Abstract

Manual waste sorting often leads to inefficient waste management and classification errors. This study implements the EfficientNetV2-B0 architecture using transfer learning and a fine-tuning strategy to classify organic and recyclable waste images from the Waste Classification Data dataset, which contains two classes. The dataset was split into 80% training, 10% validation, and 10% testing data. The methodology included image preprocessing through resizing, float32 data type conversion, and the use of EfficientNetV2-B0 internal preprocessing, followed by data augmentation, transfer learning, and fine-tuning of the last 30% of model layers using the Adam optimizer. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics under two batch size settings, 16 and 32. The results showed that a batch size of 32 achieved the best performance, with 96.45% accuracy, 96.20% precision, 95.77% recall, and 95.99% F1-score. These findings demonstrate the effectiveness of EfficientNetV2-B0 for waste image classification and its potential for automated waste sorting systems in various real-world environmental management applications. Keywords: Efficientnetv2-B0; Waste Classification; Transfer Learning; Fine-Tuning; Deep Learning   Abstrak Pemilahan sampah yang masih dilakukan secara manual sering menyebabkan proses pengelolaan sampah menjadi tidak efisien dan rentan terhadap kesalahan klasifikasi. Penelitian ini bertujuan mengimplementasikan arsitektur EfficientNetV2-B0 berbasis transfer learning dengan strategi fine-tuning untuk mengklasifikasikan citra sampah organik dan recyclable menggunakan dataset Waste Classification Data yang terdiri atas dua kelas. Dataset dibagi menjadi 80% data pelatihan, 10% data validasi, dan 10% data pengujian. Tahapan penelitian dilakukan melalui preprocessing berupa resizing, konversi tipe data, dan pemanfaatan preprocessing internal EfficientNetV2-B0, augmentasi data, transfer learning, serta fine-tuning pada 30% lapisan terakhir model dengan menggunakan optimizer Adam. Evaluasi kinerja dilakukan menggunakan metrik accuracy, precision, recall, dan F1-score dengan membandingkan dua skenario batch size, yaitu 16 dan 32. Hasil penelitian menunjukkan bahwa batch size 32 mampu menghasilkan performa terbaik dengan accuracy 96,45%, precision 96,20%, recall 95,77%, dan F1-score 95,99%. Hasil ini menunjukkan bahwa EfficientNetV2-B0 dengan strategi fine-tuning efektif dalam mengklasifikasikan citra sampah serta berpotensi mendukung pengembangan sistem pemilahan sampah otomatis.
Analisis Sentimen Berbasis Aspek untuk Mendukung Pengambilan Keputusan pada Industri Perhotelan Christevent, Kornelius Vincent; Siregar, Ivan Michael; Sirait, Tamsir Hasudungan
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol. 15 No. 4 (2026): Agustus 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i4.3803

Abstract

Guest reviews on Online Travel Agents have become an important source for assessing hotel service quality, yet conventional sentiment analysis only produces an overall score and fails to capture opinions on specific service aspects, making it difficult to determine improvement priorities. This study aims to build an Aspect-Based Sentiment Analysis (ABSA) framework that turns reviews into actionable service-improvement recommendations. Reviews from several platforms were collected, labeled, and classified using a fine-tuned IndoBERT model to identify seven service aspects along with their sentiment polarity, after which the results were summarized and presented through an interactive monitoring dashboard. The proposed model achieved 92.83% accuracy, 92.89% weighted F1, and 74.55% macro F1. These results show that the proposed framework delivers more interpretable and targeted insights than conventional sentiment analysis, thereby supporting data-driven decision-making for service improvement in the hospitality industry. Keywords: Aspect-Based Sentiment Analysis; IndoBERT; Hotel Reviews; Monitoring Dashboard; Online Travel Agent   Abstrak Ulasan tamu di Online Travel Agent menjadi sumber penting untuk menilai kualitas layanan hotel, namun analisis sentimen konvensional hanya menghasilkan skor keseluruhan dan gagal menangkap opini pada aspek layanan tertentu, sehingga sulit menentukan prioritas perbaikan. Penelitian ini bertujuan membangun kerangka kerja Analisis Sentimen Berbasis Aspek (ABSA) yang mengubah ulasan menjadi rekomendasi perbaikan layanan yang dapat ditindaklanjuti. Ulasan dari beberapa platform dikumpulkan, dilabeli, lalu diklasifikasikan menggunakan model IndoBERT yang disempurnakan untuk mengenali tujuh aspek layanan beserta polaritas sentimennya, kemudian hasilnya diringkas dan disajikan melalui dashboard pemantauan interaktif. Model yang diusulkan mencapai akurasi 92,83%, F1 tertimbang 92,89%, dan F1 makro 74,55%. Hasil ini menunjukkan bahwa kerangka kerja yang diusulkan memberikan wawasan yang lebih interpretatif dan tepat sasaran dibanding analisis sentimen konvensional, sehingga mendukung pengambilan keputusan perbaikan layanan berbasis data di industri perhotelan.
Perancangan Antarmuka dan Alur Kerja Dashboard Web untuk Manajemen Data Survei Frekuensi Radio Multi-Lokasi M Habiburrahman; Ade Silvia Handayani; Suroso Suroso; Ciksadan Ciksadan
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol. 15 No. 4 (2026): Agustus 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i4.3837

Abstract

Manual radio frequency survey documentation is prone to procedural inconsistency and inefficiency among team members, requiring a structured digital interface. This study aims to design and evaluate the user interface (UI) and workflow of a web-based dashboard to support structured and efficient radio frequency survey documentation. The method used is a case study comprising user needs analysis, wireframe design, Flask-based prototype development, and a usability walkthrough involving five survey team members. The developed system includes survey location management, documentation of three measurement sessions per location, structured file upload, and job status monitoring via visual indicators. Evaluation results show an average System Usability Scale (SUS) score of 78.5, categorized as Good, with average task completion times of 42 seconds for adding a new location and 38 seconds for uploading a session recording. These findings indicate that guided interfaces and standardized workflows improve documentation efficiency and accelerate the adaptation of new users. Keywords: Web Dashboard; User Interface; Workflow; Usability; Radio Frequency Survey   Abstrak Dokumentasi survei frekuensi radio secara manual rentan terhadap variasi prosedur antar anggota tim dan kurang efisien, sehingga diperlukan antarmuka digital yang terstruktur untuk mendukung proses tersebut. Penelitian ini bertujuan merancang dan mengevaluasi antarmuka pengguna (UI) serta workflow dashboard berbasis web guna mendukung dokumentasi survei frekuensi radio secara terstruktur dan efisien. Metode yang digunakan adalah studi kasus meliputi analisis kebutuhan pengguna, perancangan wireframe, pengembangan prototipe berbasis Flask, serta evaluasi keterpakaian melalui usability walkthrough terhadap lima anggota tim survei. Sistem yang dikembangkan mencakup pengelolaan lokasi survei, dokumentasi tiga sesi pengukuran per lokasi, upload berkas terstruktur, dan pemantauan status pekerjaan melalui indikator visual. Hasil evaluasi menunjukkan skor System Usability Scale (SUS) rata-rata 78,5 (kategori Good), dengan rata-rata waktu penyelesaian tugas 42 detik untuk menambahkan lokasi baru dan 38 detik untuk mengunggah rekaman sesi. Temuan ini juga menunjukkan bahwa antarmuka terpandu dan alur kerja terstandarisasi meningkatkan efisiensi dokumentasi serta mempercepat adaptasi pengguna baru.
Implementasi Algoritma Naïve Bayes dan Decision Tree pada Sentimen Dampak Bencana Hidrometoeorologi Arry Wahyu Setiawan; Suprianto Suprianto; Yunianita Rahmawati; Suhendro Busono
Jutisi : Jurnal Ilmiah Teknik Informatika dan Sistem Informasi Vol. 15 No. 4 (2026): Agustus 2026
Publisher : STMIK Banjarbaru

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35889/jutisi.v15i4.3858

Abstract

Abstract Hydrometeorological disasters often trigger public responses on social media, so it’s requiring analysis public opinion toward such disaster.  This study compares the performance of Decision Tree and Naïve Bayes Algorithm to analyze performance on analyzing sentiments of respond related to hydrometeorological disaster. The dataset that used contains of 11890 comments. Comments labeled into Positive, Negative, and neutral then processed by preprocessing, TF-IDF weighting, and classification with 5-fold cross validation. Validation results Naïve Bayes had mean accuracy by 0.79 which higher than Decision Tree, which scored 0,65. Naïve Bayes also got 0.79 score on accuracy, precision, recall, and F1-Score compares to Decision tree that scored scored 0.63, 0.70, 0.63, and 0.64 respectively. Because the gap of the mean accuracy and test accuracy wasn’t far off, concludes that Naïve Bayes have better generalization than Decision Tree. This result shows that Naïve Bayes is better than Decision Tree on classification of Hydrometeorological Disaster respond. Key Words: Sentiment Analysis; Hydrometeorology Disaster; Naïve Bayes; Decision tree; TF-IDF; Social Media   Abstrak Bencana hidrometeorologi memicu berbagai respons masyarakat di media sosial. maka diperlukan analisis untuk memahami opini publik terhadap bencana terkait. Tujuan penelitian ini adalah membandingkan kinerja algoritma Naïve Bayes dan Decision Tree dalam melakukan analisis sentimen terkait bencana Hidrometeorologi. Data digunakan berasal dari TikTok, Instagram Facebook yang terdiri dari 11.890 komentar dengan label kelas positif, negatif, dan netral yang kemudian diproses melalui tahapan pra-pemrosesan, pembobotan TF-IDF, dan klasifikasi dan validasi 5-fold cross validation. Hasil validasi menunjukkan Naïve Bayes memperoleh mean accuracy 0,79 lebih tinggi daripada Decision Tree yang mendapat skor 0,65. Pada data uji, Naïve Bayes memperoleh accuracy, precision, recall, dan F1-Score yang seragam 0,79 lebih unggul dari Decision Tree dengan accuracy 0,63, precision 0,70, recall 0,63, dan F1-score 0,64. Dikarenakan jarak mean acmecuracy dan test accuracy berdekatan disimpulkan Naïve Bayes mempunyai kemampuan generalisasi lebih baik daripada Decision Tree. Hasil ini menunjukkan Naïve Bayes unggul dalam mengklasifikasi sentimen terkait bencana Hidrometeorologi

Page 112 of 113 | Total Record : 1128

 109   110   111   112   113 

Filter by Year

2013 2026


Reset
Filter By Issues
All Issue Vol. 15 No. 4 (2026): Agustus 2026 Vol. 15 No. 3 (2026): Juni 2026 Vol 15, No 3 (2026): Juni 2026 Vol 15, No 2 (2026): April 2026 Vol. 15 No. 1 (2026): Februari 2026 Vol 15, No 1 (2026): Februari 2026 Vol 14, No 3: Desember 2025 Vol 14, No 2: Agustus 2025 Vol. 14 No. 2: Agustus 2025 Vol 14, No 1: April 2025 Vol 13, No 3: Desember 2024 Vol 13, No 2: Agustus 2024 Vol 13, No 1: April 2024 Vol 12, No 3: Desember 2023 Vol 12, No 2: Agustus 2023 Vol 12, No 1: April 2023 Vol 11, No 3: Desember 2022 Vol 11, No 2: Agustus 2022 Vol 11, No 1: April 2022 Vol 10, No 3: Desember 2021 Vol 10, No 2: Agustus 2021 Jutisi Vol. 10, No. 1, April 2021 JUTISI Vol. 9, No. 3, Desember 2020 JUTISI Vol. 9, No. 2, Agustus 2020 JUTISI Vol. 9, No. 1, April 2020 JUTISI Vol. 8, No. 3, Desember 2019 JUTISI Vol. 8, No. 2, Agustus 2019 JUTISI Vol. 8, No. 1, April 2019 Vol 7, No 3: Desember 2018 Vol 7, No 2: Agustus 2018 Vol 7, No 1: April 2018 Vol 6, No 3: Desember 2017 Vol 6, No 2: Agustus 2017 Vol 6, No 1: April 2017 Vol 5, No 3: Desember 2016 Vol 5, No 2: Agustus 2016 Vol 5, No 1: April 2016 Vol 4, No 3: Desember 2015 Vol 4, No 2: Agustus 2015 Vol 4, No 1: April 2015 Vol 3, No 3: Desember 2014 Vol 3, No 2: Agustus 2014 Vol 3, No 1: April 2014 Vol 2, No 1: April 2013 More Issue