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 1,096 Documents
 106   107   108   109   110 
Model Aplikasi Sistem Penerbitan Surat Cuti Pegawai Berbasis web Menggunakan Metode RAD Rosmini S; Anisah Anisah
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.v15i3.3654

Abstract

Manual employee leave administration processes cause delays in approval, recording errors, and difficulties in monitoring submission status. These problems occur at the Ministry of Human Rights (Kemenham) Bangka Belitung Islands in issuing employee leave letters. This study aims to design a web-based Employee Leave Letter Issuance System using the Rapid Application Development (RAD) method through requirements planning, user design, construction, and cutover stages. The system includes login, employee data, online leave requests, hierarchical approval, and leave reports. Results show that the system improves administrative service effectiveness, accelerates submission and approval processes, minimizes data errors, and enables real-time monitoring. This system is expected to support bureaucratic digital transformation within Kemenham Babel. Keywords: Information System; Employee Leave Letter; Rapid Application Development; Web; Employee.AbstrakProses administrasi cuti pegawai yang masih manual menyebabkan keterlambatan persetujuan, kesalahan pencatatan, serta kesulitan monitoring status pengajuan. Permasalahan tersebut terjadi pada Kantor Wilayah Kementerian Hak Asasi Manusia (Kemenham) Kepulauan Bangka Belitung dalam penerbitan surat cuti pegawai. Penelitian ini bertujuan merancang Sistem Penerbitan Surat Cuti Pegawai berbasis web menggunakan metode Rapid Application Development (RAD) melalui tahapan requirements planning, user design, construction, dan cutover. Sistem dikembangkan dengan fitur login, data pegawai, permohonan cuti online, persetujuan berjenjang, approval, dan laporan cuti. Hasil penelitian menunjukkan bahwa sistem mampu meningkatkan efektivitas layanan administrasi, mempercepat proses pengajuan dan persetujuan cuti, meminimalkan kesalahan data, serta mempermudah monitoring status secara real-time. Sistem ini diharapkan mendukung transformasi digital birokrasi di lingkungan Kantor Wilayah Kementerian HAM (Kemenham) Kep. Babel. 
Metode SMART untuk Pengembangan Sistem Penentuan Penerima Bantuan Sosial Muslihuddin Muslihuddin; Nidia Rosmawanti; Eka Chandra Kirana
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.v15i3.3676

Abstract

The distribution of social assistance often fails to reach the intended recipients due to a manual and subjective beneficiary selection process that lacks standardized weighting criteria. This study aims to develop an information technology-based Decision Support System (DSS) capable of eliminating such subjectivity. The research employs a DSS modeling approach using the Simple Multi-Attribute Rating Technique (SMART) algorithm to process complex data through the systematic application of weights and multi-criteria preferences. System functionality and consistency were evaluated using User Acceptance Testing (UAT). Test results demonstrate that the SMART method successfully provides objective and measurable recommendations for assistance recipients, achieving an accuracy rate of 91.2% when compared against actual field data. The study concludes that the developed system is valid and suitable for implementation to ensure the targeted distribution of social assistance.Keywords: Social Assistance; Decision Support System; Simple Multi-Attribute Rating Technique; Multi-Criteria Decision Making. AbstrakPenyaluran bantuan sosial sering kali tidak tepat sasaran akibat proses penentuan penerima yang masih manual dan subjektif tanpa adanya standarisasi pembobotan kriteria. Penelitian ini bertujuan untuk mengembangkan Sistem Pendukung Keputusan (SPK) berbasis teknologi informasi yang mampu menghilangkan subjektivitas tersebut. Metode penelitian yang diterapkan adalah pemodelan SPK menggunakan algoritma Simple Multi-Attribute Rating Technique (SMART) untuk mengolah data kompleks melalui pemberian bobot dan nilai preferensi multi-kriteria secara sistematis. Evaluasi fungsionalitas dan keandalan sistem diukur menggunakan pengujian User Acceptance Testing (UAT). Hasil pengujian sistem membuktikan bahwa metode SMART berhasil memberikan rekomendasi penerima bantuan secara objektif dan terukur, dengan tingkat akurasi mencapai 91,2% jika dicocokkan dengan data riil di lapangan. Simpulan dari penelitian ini menunjukkan bahwa sistem yang dibangun valid dan layak diimplementasikan untuk menjamin penyaluran bantuan sosial yang tepat sasaran. 
Analisis dan Penerapan Hybrid Cloud dalam Backup Data Multimedia pada Kegiatan Liputan dan Livestreaming Ridho Hari Septiansyah; Kiswanto Kiswanto
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.v15i3.3692

Abstract

Multimedia data management in coverage and livestreaming activities had a high risk of data loss when using conventional local storage methods. This study aimed to analyze and implement a hybrid cloud-based multimedia data backup system for coverage and livestreaming activities at CV. Lesmana Jaya. The research applied the Prototyping method through problem identification, system requirements analysis, system design, implementation, and testing stages. The implemented system integrated local storage and cloud-based storage to support multimedia data backup and distribution processes. The results showed that the implementation of the hybrid cloud system improved the security and effectiveness of multimedia data management. Based on system testing, the proposed system increased backup process efficiency by 65.6% compared to the previous method and accelerated multimedia data distribution to editors and clients.Keywords: Hybrid cloud; Data backup; Multimedia; Livestreaming; Cloud storage AbstrakPengelolaan data multimedia pada kegiatan liputan dan livestreaming memiliki risiko kehilangan data yang cukup tinggi apabila masih menggunakan metode penyimpanan manual berbasis media lokal. Penelitian ini bertujuan untuk menganalisis dan menerapkan sistem backup data multimedia berbasis hybrid cloud pada kegiatan liputan dan livestreaming di CV. Lesmana Jaya. Metode penelitian yang digunakan adalah Prototyping dengan tahapan identifikasi masalah, analisis kebutuhan sistem, perancangan sistem, implementasi, dan pengujian sistem. Sistem yang diterapkan mengintegrasikan penyimpanan lokal dan penyimpanan berbasis cloud untuk mendukung proses backup dan distribusi data multimedia. Hasil penelitian menunjukkan bahwa penerapan sistem hybrid cloud mampu meningkatkan keamanan dan efektivitas pengelolaan data multimedia. Berdasarkan hasil pengujian, sistem berhasil meningkatkan efisiensi proses backup data sebesar 65,6% dibandingkan metode sebelumnya serta mempercepat proses distribusi data kepada editor dan klien. 
Pengembangan Digital Acquisition Product Sebagai Layanan Pelanggan di Industri Perbankan Intan Ardiani Putri; Jap Tji Beng; Rahmiyana Nurkholiza; Vienchenzia Oeyta Dwitama Dinatha
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.v15i3.3737

Abstract

This study evaluates the success of Digital Acquisition Product development through the implementation of the Quick Response Code Indonesian Standard payment system at Bank X using a computational data analytics approach. Most previous studies have focused on consumer adoption through perception-based surveys, leaving a research gap in evaluating the operational capacity of internal banking systems. This study processes real transactional Big Data from 2023 to April 2026 using the Python programming language within the Google Colab environment. The computational stages include data wrangling using the Pandas library, data structure transformation (melting), missing value handling, and the development of custom algorithms to standardize time-log formats. The novelty of this study lies in the application of computational scripts to validate system performance longitudinally. The computational analysis of the 2026 projected data indicates high system scalability, as evidenced by the dominance of transaction loads through digital channels, accounting for 96.1 percent of total transactions compared to physical infrastructure. The study concludes that the Digital Acquisition Product architecture has proven robust in handling increasing data traffic and recommends that banking institutions begin integrating predictive algorithms to ensure the sustainability of the digital server ecosystem.Keywords: Data Analytics; System Evaluation; Descriptive Computing; Python; Digital Acquisition Product.AbstrakPenelitian ini mengevaluasi keberhasilan pengembangan Digital Acquisition Product melalui implementasi sistem pembayaran Quick Response Code Indonesian Standard pada Bank X menggunakan pendekatan data analytics komputasional. Sebagian besar penelitian terdahulu berfokus pada adopsi konsumen melalui survei persepsi, sehingga menyisakan kesenjangan analisis pada evaluasi kapasitas operasional sistem internal perbankan. Penelitian ini memproses data transaksional riil (Big Data) periode 2023 hingga April 2026 menggunakan bahasa pemrograman Python di lingkungan Google Colab. Tahapan komputasi mencakup data wrangling menggunakan pustaka Pandas, transformasi struktur data (melting), penanganan missing values, serta pembuatan algoritma kustom untuk standardisasi format log waktu. Kebaruan studi ini terletak pada penerapan script komputasi untuk memvalidasi performa sistem secara longitudinal. Hasil analisis komputasi pada proyeksi data 2026 menunjukkan skalabilitas sistem yang tinggi, ditandai dengan dominasi beban transaksi pada kanal digital sebesar 96,1 persen dibandingkan infrastruktur fisik. Penelitian ini menyimpulkan bahwa pengembangan arsitektur Digital Acquisition Product terbukti tangguh dalam menangani lonjakan traffic data, dan perbankan disarankan mulai mengintegrasikan algoritma prediktif untuk menjaga keberlanjutan ekosistem server digital. 
Analisis IT Service Management Menggunakan Framework ITIL V4 pada RSUP Dr. Mohammad Hoesin Kota Palembang Dedi Ferdinan Manalu; Dicky Pratama
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.v15i3.3719

Abstract

Information Technology Service Management plays a crucial role in supporting effective and sustainable hospital operations. Dr. Mohammad Hoesin General Hospital, Palembang City, still faces several IT service challenges, such as system and network disruptions, and suboptimal service management. This study aims to analyze the maturity level of IT services using the ITIL V4 Framework in Incident Management, Problem Management, and Service Continuity Management practices. The study used a mixed methods approach with observation, interviews, literature studies, and questionnaires. The results showed that the maturity level of Incident Management practices was 4.1, Problem Management was 4.04, and Service Continuity Management was 3.94, which are at Level 4 (Managed). This study resulted in recommendations for the development of IT service SOPs, improved system monitoring, and strengthened documentation and backup recovery processes.Keywords: IT Service Management; ITIL V4; Incident Management; Problem Management; Service Continuity Management. AbstrakPengelolaan layanan teknologi informasi memiliki peranan penting dalam mendukung operasional rumah sakit agar berjalan efektif dan berkelanjutan. RSUP Dr. Mohammad Hoesin Kota Palembang masih menghadapi beberapa kendala layanan TI seperti gangguan sistem, jaringan, dan pengelolaan layanan yang belum optimal. Penelitian ini bertujuan untuk menganalisis tingkat kematangan layanan TI menggunakan Framework ITIL V4 pada praktik Incident Management, Problem Management, dan Service Continuity Management. Penelitian menggunakan pendekatan mixed methods dengan teknik observasi, wawancara, studi literatur, dan kuesioner. Hasil penelitian menunjukkan nilai maturity level pada praktik Incident Management sebesar 4,1, Problem Management sebesar 4,04, dan Service Continuity Management sebesar 3,94 yang berada pada Level 4 (Managed). Penelitian ini menghasilkan rekomendasi berupa penyusunan SOP layanan TI, peningkatan monitoring sistem, serta penguatan dokumentasi dan proses backup recovery. 
Implementasi dan Optimasi Server JupyterHub sebagai Pendukung Pembelajaran di Laboratorium Informatika Universitas Janabadra Sri Rahayu; Muhammad Fuad
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.v15i3.3453

Abstract

Python programming laboratories often encounter challenges related to inconsistent software configurations, library installation errors, and the lack of centralized management of the practical learning environment. This study aims to design and implement JupyterHub as a centralized Python laboratory environment based on a local server at the Informatics Laboratory of Universitas Janabadra. The study employed an applied experimental approach consisting of system requirements analysis, architecture design, service implementation, and multi-user performance testing and evaluation. The results demonstrate that the proposed system was successfully implemented according to the designed architecture. JupyterHub and the Dask cluster operated in an integrated manner, while user authentication, automated user management, and resource optimization through the Idle Culler mechanism functioned effectively. Furthermore, monitoring using the Dask Dashboard indicated that computational tasks were successfully distributed across the cluster with stable server resource utilization. These findings indicate that the proposed system provides a reliable, centralized, and efficient environment for supporting Python programming laboratories in higher education. Keywords: JupyterHub; Laboratory; Python; Practical Learning; Centralized Server   Abstrak Pelaksanaan praktikum pemrograman Python di laboratorium komputer sering menghadapi permasalahan perbedaan konfigurasi perangkat, kesalahan instalasi pustaka, serta keterbatasan pengelolaan lingkungan praktikum secara terpusat. Penelitian ini bertujuan merancang dan mengimplementasikan JupyterHub sebagai lingkungan praktikum Python terpusat berbasis server lokal di Laboratorium Informatika Universitas Janabadra. Pendekatan yang digunakan adalah eksperimen terapan melalui tahapan analisis kebutuhan, perancangan arsitektur sistem, implementasi layanan, serta pengujian dan evaluasi performa multiuser. Hasil penelitian menunjukkan bahwa sistem berhasil diimplementasikan sesuai rancangan, layanan JupyterHub dan cluster Dask berfungsi secara terintegrasi, serta mekanisme autentikasi, otomatisasi manajemen pengguna, dan optimasi sumber daya melalui Idle culler berjalan dengan baik. Monitoring menggunakan Dashboard Dask menunjukkan bahwa distribusi komputasi berlangsung secara normal dengan penggunaan sumber daya server yang stabil. Kata kunci: JupyterHub; Laboratorium; Python; Praktikum; Server Terpusat
Analisis Kesuksesan Sistem Informasi Akademik Menggunakan Delone & Mclean Is Success Model Ghiffari, Fahmi Al; Fauzi, Izaz Muhamad; Maulid, Fajril
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.v15i3.3570

Abstract

Diigiital transfoirmatiioin has changed hoiw hiigher educatiioin iinstiitutiioins manage academiic serviices. Thiis study evaluates the success oif SEVIiMA SiiAkadCloiud at Iinstiitut Pendiidiikan Iindoinesiia Garut by coimbiiniing the DeLoine and McLean Iinfoirmatiioin System Success Moidel wiith selected coinstructs froim the Technoiloigy Acceptance Moidel. The study used a quantiitatiive survey iinvoilviing 280 actiive students selected throiugh purpoisiive sampliing. Data were proicessed usiing coivariiance-based Structural Equatiioin Moideliing. The fiindiings iindiicate that System qualiity, iinfoirmatiioin qualiity, and Serviice qualiity have siigniifiicant effects oin system use. Perceiived ease oif use and system use alsoi have siigniifiicant effects oin user satiisfactiioin. Net benefiit iis maiinly explaiined by actual system use. These results shoiw that the value oif an academiic iinfoirmatiioin system iis shaped noit oinly by techniical qualiity, but alsoi by the extent toi whiich students use the system iin theiir academiic actiiviitiies.Keywords: Academiic Iinfoirmatiioin System; DeLoine & McLean; SEM; TAM  AbstrakPerubahan layanan pendiidiikan tiinggii menuju siistem diigiital membuat perguruan tiinggii perlu meniilaii keberhasiilan siistem iinfoirmasii akademiik secara lebiih terukur. Peneliitiian iinii menganaliisiis keberhasiilan iimplementasii SEVIiMA SiiAkadCloiud dii Iinstiitut Pendiidiikan Iindoinesiia Garut dengan menggabungkan DeLoine and McLean IiS Success Moidel dan koinstruk Technoiloigy Acceptance Moidel. Peneliitiian menggunakan pendekatan kuantiitatiif melaluii surveii terhadap 280 mahasiiswa aktiif yang diipiiliih dengan tekniik purpoisiive sampliing. Data diianaliisiis menggunakan Structural Equatiioin Moideliing berbasiis koivariians. Hasiil peneliitiian menunjukkan bahwa kualiitas siistem, kualiitas iinfoirmasii, dan kualiitas layanan berpengaruh siigniifiikan terhadap penggunaan siistem. Perceiived ease oif use dan penggunaan siistem berpengaruh siigniifiikan terhadap kepuasan pengguna. Manfaat bersiih siistem lebiih banyak diitentukan oileh penggunaan aktual. Temuan iinii menunjukkan bahwa keberhasiilan siistem iinfoirmasii akademiik tiidak hanya bergantung pada kualiitas tekniis, tetapii juga pada iintensiitas pemanfaatan siistem oileh mahasiiswa dalam layanan akademiik. 
Rancang Bangun Sistem Informasi Manajemen Proyek Event Organizer Berbasis Software as a Service Menggunakan Laravel salman fahrurroji; Yopi Nugraha
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.v15i3.3678

Abstract

Limited transparency and sub-optimal real-time monitoring within the Event Organizer (EO) industry represent significant challenges that diminish Client trust. This research aims to develop a web-based project management system using a Software as a Service (SaaS) approach to bridge the information gap between admins and Clients. The system is developed using the Agile Scrum methodology, leveraging the Laravel framework and a multi-tenant database architecture to ensure scalability and secure data isolation among Users. Black Box Testing results indicate that all system functionalities operate successfully with a 100% success rate. Performance evaluation Validates the efficiency of the multi-tenant architecture, yielding an average response time of under 3 seconds. Furthermore, the User Acceptance Test (UAT) results achieved a score of 4.4 out of 5.0, with the highest rating in the transparency and monitoring aspect. The implementation of this system not only enhances the operational accountability of EOs and mitigates communication risks but also provides digital infrastructure cost efficiency for MSMEs through a centralized SaaS ecosystem. Keywords: Project Management; Event Organizer; Saas; Laravel; Multi-tenant   Abstrak Keterbatasan transparansi dan belum optimalnya pemantauan secara waktu nyata (real-time) dalam industri Event Organizer (EO) menjadi kendala utama yang menurunkan kepercayaan client. Penelitian ini bertujuan mengembangkan sistem manajemen proyek berbasis web dengan pendekatan Software as a Service (SaaS) guna menjembatani kesenjangan informasi (information gap) antara admin dan client. Sistem dibangun menggunakan metode Agile Scrum dengan memanfaatkan framework Laravel dan arsitektur basis data multi-tenant untuk menjamin skalabilitas serta isolasi data antar pengguna secara aman. Hasil pengujian Black Box menunjukkan fungsionalitas sistem berjalan 100%. Evaluasi performa membuktikan efisiensi arsitektur multi-tenant dengan waktu respons rata-rata di bawah 3 detik. Sementara itu, User Acceptance Test (UAT) memperoleh skor 4,4 dari skala 5,0, dengan penerimaan tertinggi pada aspek transparansi pemantauan. Implementasi sistem ini tidak hanya memperkuat akuntabilitas operasional EO dan mengurangi risiko miskomunikasi, tetapi juga menawarkan efisiensi biaya infrastruktur digital bagi UMKM melalui ekosistem SaaS terpusat. Kata kunci: Manajemen Proyek; Event Organizer; Saas; Laravel; Multi-tenant
Analisis Sentimen Pengunduran Menteri Keuangan dan Dampaknya terhadap IHSG dengan Naive Bayes M. Saiful Bahri; Mohammad Zainuddin
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.v15i4.3686

Abstract

The resignation of Indonesia’s Minister of Finance in 2025 generated substantial public attention on social media and sparked concerns about its possible implications for the Indonesia Composite Stock Price Index (IHSG). This study investigates public sentiment related to the event and evaluates its association with IHSG performance. The analysis utilized 4,655 Twitter/X posts collected between 21 August and 26 September 2025. Public sentiment was classified using the Multinomial Naive Bayes algorithm combined with TF-IDF feature weighting, while the relationship between sentiment indicators and IHSG fluctuations was assessed through Spearman rank correlation and Ordinary Least Squares (OLS) regression. The sentiment classification model demonstrated strong performance, achieving 82.53% accuracy and an AUC value of 0.960. Negative sentiment accounted for the largest proportion of online discussions (46.1%). The results reveal that public sentiment did not exert a significant influence on IHSG movements within the same trading day. However, positive sentiment from the preceding period significantly affected the subsequent day’s IHSG log-return (β = 0.0322; p = 0.033), indicating that market reactions to social media sentiment tend to occur with a temporal delay. Keywords: Sentiment analysis; IHSG; Naive Bayes; TF-IDF; Social media   Abstrak Pengunduran diri Menteri Keuangan Republik Indonesia pada tahun 2025 memicu perhatian luas masyarakat di media sosial dan menimbulkan kekhawatiran mengenai potensi dampaknya terhadap pergerakan Indeks Harga Saham Gabungan (IHSG). Penelitian ini bertujuan menganalisis sentimen publik yang muncul terkait peristiwa tersebut serta mengkaji hubungannya dengan dinamika IHSG. Data penelitian terdiri atas 4.655 unggahan Twitter/X yang dikumpulkan selama periode 21 Agustus hingga 26 September 2025. Analisis sentimen dilakukan menggunakan algoritma Multinomial Naive Bayes dengan pembobotan TF-IDF, sedangkan hubungan antara sentimen dan pergerakan IHSG dianalisis melalui korelasi Spearman dan regresi Ordinary Least Squares (OLS). Hasil pengujian menunjukkan bahwa model klasifikasi memiliki kinerja yang baik dengan tingkat akurasi sebesar 82,53% dan nilai AUC sebesar 0,960. Sentimen negatif mendominasi percakapan publik dengan proporsi 46,1%. Temuan penelitian mengindikasikan bahwa sentimen publik tidak memberikan pengaruh yang signifikan terhadap pergerakan IHSG pada hari perdagangan yang sama. Namun, sentimen positif pada periode sebelumnya terbukti berpengaruh signifikan terhadap log-return IHSG pada hari berikutnya (β = 0,0322; p = 0,033). Hasil ini menunjukkan adanya respons pasar yang tertunda terhadap sentimen publik yang berkembang di media sosial. Kata kunci: Analisis sentimen; IHSG; Naive Bayes; TF-IDF; Media Sosial
Evaluasi Performa Algoritma Klasterisasi dalam Mengelompokkan Topik Tugas Akhir: Studi Komparasi K-Means dan DBSCAN Tifanny Nabarian; Dhea Marsella; Salman El Farisi
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.v15i3.3759

Abstract

The increasing number of Informatics Engineering students at STT-NF has resulted in a growing volume of final project topics that need to be efficiently categorized into research areas. This study evaluates the performance of the K-Means and DBSCAN algorithms for clustering students' final project topics based on their textual characteristics. The research follows the CRISP-DM framework and utilizes a dataset of 656 final project titles. The data were processed through text preprocessing, TF-IDF weighting, and dimensionality reduction PCA. The experimental results indicate that K-Means with k = 13 achieved the best performance, obtaining a silhouette score of 0.1434 and a purity score of 0.8659, outperforming DBSCAN, which achieved a silhouette score of 0.1153 and a purity score of 0.6589. The resulting clusters were successfully mapped into four major research areas, namely Software Engineering, Network Engineering & Cyber Security, Data Engineering, and UI/UX Design. Furthermore, the best-performing model was implemented in an interactive Streamlit-based dashboard to support research area mapping and academic supervisor assignment. Keywords: K-Means; DBSCAN; Final Project Topic Clustering; TF-IDF   Abstrak Peningkatan jumlah mahasiswa Teknik Informatika di STT-NF menghasilkan semakin banyak data topik tugas akhir yang perlu dikelompokkan ke dalam bidang penelitian secara efisien. Penelitian ini mengevaluasi performa algoritma K-Means dan DBSCAN untuk mengelompokkan topik tugas akhir mahasiswa berdasarkan kemiripan karakteristiknya. Proses penelitian mengikuti metodologi CRISP-DM dengan menggunakan 656 judul tugas akhir yang diproses melalui tahapan pemrosesan teks, pembobotan TF-IDF, dan reduksi dimensi PCA. Berdasarkan hasil pengujian, K-Means dengan k = 13 memberikan kinerja terbaik dengan nilai silhouette score 0.1434 dan purity 0.8659, sedangkan DBSCAN memperoleh nilai silhouette score 0.1153 dan purity 0.6589. Klaster yang terbentuk berhasil direpresentasikan ke dalam empat bidang penelitian utama, yaitu Software Engineering, Network Engineering & Cyber Security, Data Engineering, dan UI/UX Design. Sebagai implementasi, model terbaik diintegrasikan ke dalam dashboard interaktif berbasis Streamlit untuk mendukung pemetaan bidang penelitian dan penentuan dosen pembimbing. Kata kunci: K-Means; DBSCAN; Klasterisasi Topik Tugas Akhir; TF-IDF

Page 109 of 110 | Total Record : 1096

 106   107   108   109   110 

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 14, No 3: Desember 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