Garuda - Garba Rujukan Digital

Sentence embedding to improve rumour detection performance model Anggrainingsih, Rini; Wihidayat, Endar Suprih; Widoyono, Bambang
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 1: March 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i1.pp115-121

Recently, most individuals have preferred accessing the most recent news via social media platforms like Twitter as their primary source of information. Moreover, Twitter enables users to post and distribute tweets quickly and unsupervised. As a result, Twitter has become a popular platform for disseminating false information, such as rumours. These rumours were then propagated as accurate and influenced public opinion and decision-making. The issue will arise when a decision or policy with substantial consequences is made based on rumours. To avoid the negative impacts of rumours, several researchers have attempted to detect them automatically as early as feasible. Previous studies employed supervised learning methods to identify Twitter rumours and relied on feature extraction algorithms to extract tweet content and context elements. However, manually extracting features is time-consuming and labour-intensive. To encode each tweet's sentence as a vector based on its contextual meaning, we proposed utilising Bidirectional Encoder Representation of Transformer (BERT) as a sentence embedding. We then used these vectors to train some classifier models to detect rumours. Finally, we compared the performance of BERT-based models to feature engineering-based models. We discovered that the suggested BERT-based model improved all parameters by around 10% compared to the feature engineering-based classification model.

Analisis Tingkat Kematangan Open Government Data Menggunakan OD-MM di Pemerintah Provinsi Aceh Sudarwono, Dianto Adwoko; Prastowo, Rahardito Dio; Ruldeviyani, Yova; Widoyono, Bambang
Jurnal Informatika Ekonomi Bisnis Vol. 6, No. 3 (September 2024)
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/infeb.v6i3.988

Pemerintah Indonesia telah memulai inisiatif open data sejak tahun 2008 dengan menerbitkan Undang-undang tentang Keterbukaan Informasi Publik. Gerakan Open Government Indonesia (OGI) yang meluncurkan Rencana Aksi Nasional (RAN) Open Government yang pertama pada tahun 2012. Implementasi Portal Open Data di Pemerintah Aceh dimulai tahun 2018 dengan tujuan optimalisasi penggunaan data dan informasi publik dalam pembangunan Aceh yang lebih baik. Namun berdasarkan data yang dianalisis bahwa terdapat beberapa kendala dalam pelaksanaan Portal Open Data seperti kekurangan SDM yang terampil, ketidakmampuan untuk mengumpulkan dan mengintegrasikan data yang relevan, kelemahan dalam keamanan data, sehingga belum dapat dipastikan apakah proses OGD telah berjalan dengan optimal atau belum. Oleh sebab itu penting dilakukan pengukuran tingkat kematangan Open Government Data (OGD) pada Pemerintah Aceh. Pengukuran tingkat kematangan menggunakan Open Data Maturity Model (OD-MM), dengan memberikan kuesioner kepada 12 pengelola Portal Open Data Aceh. Dari hasil pengukuran diperoleh hasil bahwa tingkat kematangan OGD Aceh berada pada level 3 dari skor maksimal 4. Sebanyak 22 rekomendasi perbaikan disampaikan untuk mengembangkan tingkat kematangan OGD Aceh ke level yang lebih tinggi. Selain itu juga dilakukan simulasi fitur roadmap generator pada OD-MM yang dapat digunakan sebagai alat self-assessment kedepannya.

Analisis Tingkat Kematangan Open Government Data Menggunakan OD-MM di Pemerintah Provinsi Aceh Sudarwono, Dianto Adwoko; Prastowo, Rahardito Dio; Ruldeviyani, Yova; Widoyono, Bambang
Jurnal Informatika Ekonomi Bisnis Vol. 6, No. 3 (September 2024)
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/infeb.v6i3.988

Pemerintah Indonesia telah memulai inisiatif open data sejak tahun 2008 dengan menerbitkan Undang-undang tentang Keterbukaan Informasi Publik. Gerakan Open Government Indonesia (OGI) yang meluncurkan Rencana Aksi Nasional (RAN) Open Government yang pertama pada tahun 2012. Implementasi Portal Open Data di Pemerintah Aceh dimulai tahun 2018 dengan tujuan optimalisasi penggunaan data dan informasi publik dalam pembangunan Aceh yang lebih baik. Namun berdasarkan data yang dianalisis bahwa terdapat beberapa kendala dalam pelaksanaan Portal Open Data seperti kekurangan SDM yang terampil, ketidakmampuan untuk mengumpulkan dan mengintegrasikan data yang relevan, kelemahan dalam keamanan data, sehingga belum dapat dipastikan apakah proses OGD telah berjalan dengan optimal atau belum. Oleh sebab itu penting dilakukan pengukuran tingkat kematangan Open Government Data (OGD) pada Pemerintah Aceh. Pengukuran tingkat kematangan menggunakan Open Data Maturity Model (OD-MM), dengan memberikan kuesioner kepada 12 pengelola Portal Open Data Aceh. Dari hasil pengukuran diperoleh hasil bahwa tingkat kematangan OGD Aceh berada pada level 3 dari skor maksimal 4. Sebanyak 22 rekomendasi perbaikan disampaikan untuk mengembangkan tingkat kematangan OGD Aceh ke level yang lebih tinggi. Selain itu juga dilakukan simulasi fitur roadmap generator pada OD-MM yang dapat digunakan sebagai alat self-assessment kedepannya.

Peningkatan Kualitas Administrasi Pendidikan melalui Implementasi Sistem Edu Berbasis ERP di SMP IT Insan Mulia Surakarta, Jawa Tengah Widoyono, Bambang; Saptono, Ristu; Rohmadi, Arif; Syaifuddin, Akhmad; Hendra, Brilyan; Anggoro, Rizal Dwi; Ibrahim, Muhammad Syafiq
Jurnal Abdi Masyarakat Indonesia Vol 5 No 6 (2025): JAMSI - November 2025
Publisher : CV Firmos

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54082/jamsi.2130

SMP Islam Insan Mulia Surakarta-Jawa Tengah, mengalami kendala administrasi akibat sistem manualnya, terutama dalam penerimaan siswa baru (PPDB), pencatatan pembayaran, dan pengelolaan bank soal. Kendala-kendala ini menyebabkan keterlambatan, kesalahan, dan inefisiensi, sehingga membatasi kualitas layanan. Untuk mengatasi hal ini, dalam program pengabdian masyarakat kami mengimplementasikan sistem EDU berbasis ERP sebagai solusi terintegrasi. Sistem ini menggunakan model waterfall untuk analisis, perancangan, implementasi, pelatihan, dan pengujian yang diterapkan selama tiga bulan. Tiga modul diimplementasikan: PPDB, pembayaran, dan bank soal, yang diuji coba kepada 23 peserta. Evaluasi menunjukkan hasil positif dengan efisiensi (4,08), efektivitas (4,08), dampak (4,38), kepuasan (4,28), dan kemudahan penggunaan (4,17) pada rentang skala 1-5. Program pengabdian ini tidak hanya menyelesaikan kendala administratif di SMP Islam Insan Mulia Surakarta, tetapi juga menghadirkan model implementasi sistem informasi berbasis ERP yang dapat direplikasi di sekolah lain. Digitalisasi administrasi melalui modul PPDB, pembayaran, dan bank soal terbukti meningkatkan efisiensi, transparansi, dan profesionalisme tata kelola pendidikan secara umum.

Information management of critical knowledge in an IT consulting company Widoyono, Bambang; Saptono, Ristu; Rohmadi, Arif; Wihidayat, Endar; Syaifuddin, Akhmad; Hendrasuryawan, Brilyan
Jurnal Kajian Informasi dan Perpustakaan Vol 14, No 1 (2026): Accredited by Ministry of Education, Culture, Research and Technology of the Re
Publisher : Universitas Padjadjaran

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24198/jkip.v14i1.67577

Background: Knowledge Management (KM) plays a crucial role in supporting organizational sustainability, particularly in IT consulting firms where knowledge is predominantly tacit, experience-based, and vulnerable to loss. Many consulting organizations face difficulties identifying which knowledge is truly critical and how to manage it as reusable organizational information. Purpose: This study aimed to identify, prioritize, and manage critical knowledge aligned with organizational strategy at PT XYZ, an IT consulting company. Methods: Using a mixed qualitative–quantitative approach, this study followed six stages: contextual knowledge scoping, tacit knowledge elicitation, knowledge structuring, critical knowledge assessment using Critical Knowledge Factors (CKF), prioritization using Analytical Hierarchy Process (AHP), and repository design for knowledge preservation. Results: The study identified 24 structured knowledge areas, of which 20 were classified as critical. AHP analysis indicated that Gaining Commitment, Reading Opportunities, and Marketing Strategy were the highest priority knowledge assets, primarily embedded in sales and marketing activities. Conclusion: This study demonstrates how tacit knowledge can be transformed into structured organizational information aligned with strategic processes through an information management perspective. Theoretically, this study contributes to information science by conceptualizing critical knowledge as information objects organized through metadata, lifecycle governance, and repository preservation. Implications: In practice, these findings provide the IT consulting firm with a structured approach to safeguarding critical tacit knowledge, reducing reliance on individuals, and strengthening organizational memory. However, the study is limited to a single organizational context, relies on expert judgment, and presents a repository design that remains conceptual rather than technically implemented.

Aspect-Based Sentiment Analysis of Access by KAI Application Reviews Using IndoBERT for Multi-Label Classification Tasks Nur Alfiana, Hilda; Doewes, Afrizal; Widoyono, Bambang
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 1 (2026): JUTIF Volume 7, Number 1, February 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.1.5402

Ratings and reviews on mobile applications provide valuable insights into user experience and satisfaction with app features and services. However, ratings are subjective and often inconsistent with the content of the reviews. Therefore, a more in-depth analysis of the review content is necessary to identify evaluation points accurately. This study aims to evaluate the performance of IndoBERT in Aspect-Based Sentiment Analysis (ABSA) on Access by KAI application reviews. Data were collected by scraping user reviews from the Google Play Store, then annotated using a hybrid labeling approach. The resulting dataset was used to fine-tune the IndoBERT model across three ABSA tasks: aspect classification, sentiment classification for each aspect, and joint aspect-sentiment classification. We also benchmarked the model against baseline models to demonstrate its effectiveness. The results show that IndoBERT achieved the best performance across all tasks, specifically aspect classification (accuracy 0.928, F1-score 0.785), sentiment classification (accuracy 0.928, F1-score 0.752), and joint aspect-sentiment classification (accuracy 0.962, F1-score 0.549). Overall, IndoBERT successfully outperformed SVM and XGBoost with TF-IDF, BiLSTM with pre-trained IndoBERT embeddings, mBERT, and XLM-R. This study contributes a new dataset that provides resources for further research and development in Indonesian Natural Language Processing (NLP). These findings also highlight the advantages of a monolingual model trained specifically on Indonesian-language data.

Optimizing E-commerce Personalization through Hybrid Decision Tree–Nearest Neighbor Recommendation Integration Syaifuddin, Akhmad; Saptono, Ristu; Rohmadi, Arif; Widoyono, Bambang; Hendrasuryawan, Brilyan
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 2 (2026): JUTIF Volume 7, Number 2, April 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.2.5418

Single-method recommendation systems face critical limitations: content-based filtering suffers from overspecialization while collaborative filtering struggles with data sparsity and cold-start problems. This research introduces an innovative hybrid recommendation framework that synthesizes Content-Based Filtering (CBF) utilizing Decision Trees with Collaborative Filtering (CF) employing Nearest Neighbor algorithms. Our approach addresses the inherent limitations of singular recommendation methodologies by integrating product attribute analysis with collective user behavior patterns. We conducted comprehensive evaluations using a shopping behavior dataset comprising 3,900 consumer records with diverse demographic and product interaction data. Our findings reveal that an asymmetric hybrid configuration—weighted at 70% for CBF and 30% for CF—achieves optimal performance with a Root Mean Square Error (RMSE) of 0.7422. The system incorporates an interactive user interface that facilitates a natural shopping experience: browsing available items, receiving personalized recommendations, and providing explicit feedback on suggested products. Through feature importance analysis, we identified key product attributes that significantly influence recommendation quality, including size variations and specific color preferences. The hybrid approach demonstrates 42% greater category diversity and 37% more recommendation diversity compared to pure content-based filtering, while maintaining superior accuracy metrics. Our research contributes to understanding optimal hybrid architectures and provides practical insights for implementing effective personalization strategies in real-world e-commerce environments.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search