Claim Missing Document
Check
Articles

Predicting Social Media Post Engagement and Virality Using Graph Neural Network Approaches and Content-based Features Fathimah Az Zahrah; Riska Dhenabayu; Muhammad Fajar Wahyudi Rahman; Renny Sari Dewi; Zamabhungane Hadebe Aminah
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 11, No. 3, August 2026
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v11i3.2686

Abstract

Social media teams increasingly rely on early signals to prioritize content, yet forecasting engagement and identifying viral posts remain difficult under temporal drift and heavy-tailed interaction counts. This study evaluated Graph Neural Network (GNN) approaches for predicting post engagement and virality from pre-posting content-based and contextual features. The Social Media Engagement Report dataset, which contained 100,000 posts across Twitter, LinkedIn, Facebook, and Instagram spanning March 2021–March 2024, was used. Post-release variables (impressions, reach, engagement rate) were excluded to prevent leakage. A homogeneous post–post graph was constructed using k-nearest-neighbor similarity in an embedding space and exact-match links on low-cardinality context. Ridge/Logistic Regression, Random Forest, and XGBoost as the baselines were compared against GraphSAGE and GAT under a chronological train, validation, and test split. Regression used MAE, RMSE, and R², while virality classification used ROC-AUC, PR-AUC, and Precision at the top 1% ranked posts. GraphSAGE yielded the strongest virality screening, achieving ROC-AUC = 0.66, PR-AUC = 0.54–0.56, and Precision@1% up to 0.75, substantially above non-graph baselines. For regression, GAT produced the lowest errors despite a negative R², indicating limited explained variance. Overall, similarity-graph GNNs are most effective for early virality identification, whereas exact count prediction remains challenging in a strictly pre-posting, time-aware setting. These findings contribute empirical evidence that, under leakage-safe pre-posting conditions, graph-based relational modeling is more useful for ranking and screening potentially viral posts than for precise engagement-count forecasting.
Evaluating the Usability of a Coconut Export Website Using the System Usability Scale (SUS) I Ketut Ari Sadhu Gunawan; Renny Sari Dewi
Sisfo: Jurnal Ilmiah Sistem Informasi Vol. 10 No. 1 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2026
Publisher : Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/sisfo.v10i1.27005

Abstract

This study aims to evaluate the usability level of the PT Palm Trade Company website in order to improve user experience and system effectiveness. The method used is the System Usability Scale (SUS) as a standardized approach to assess users' perceptions of the ease of system use. Data were collected through the distribution of questionnaires to respondents who had directly interacted with the website. The obtained data were analyzed to generate usability scores and to evaluate various levels of user satisfaction. The results of the study indicate that the website falls into the acceptable category, suggesting that the system is generally easy to use and capable of meeting user expectations. However, there are aspects that require further improvement, particularly in terms of interface design and navigation efficiency. The analysis of the coconut export website generally meets usability standards, but requires ongoing improvements to enhance the user experience and support the effectiveness of export transactions. Recommendations for improvement are expected to serve as a guide for developers in optimizing the quality of digital services. In addition, several issues were identified related to information consistency and visual appearance. Based on these findings, several recommendations are proposed to enhance the overall quality and performance of the website. This study concludes that usability evaluation plays an important role in supporting digital platforms, especially in complex agribusiness companies.
Digital Capability, Digital Transformation, and Digital Innovation as Determinants of Food Stall Business Performance in South Tangerang City Rayhan Aimar Nawawi; Hujjatullah Fazlurrahman; Renny Sari Dewi; Achmad Kautsar
JURNAL ECONOMINA Vol. 5 No. 5 (2026): JURNAL ECONOMINA, Mei 2026
Publisher : LPPM Sekolah Tinggi Ilmu Ekonomi 45 Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55681/economina.v5i5.2146

Abstract

This study is motivated by the rapid digitalization of Micro, Small, and Medium Enterprises (MSMEs) in Indonesia, particularly through online ordering platforms, delivery services, social media, and digital payment systems such as QRIS. However, digital adoption does not always improve business performance, especially among food stall MSMEs that still face challenges such as declining profit margins, platform dependency, and limited internal readiness. This study aims to analyze the influence of Digital Capability, Digital Transformation, and Digital Innovation on the Business Performance of food stall MSMEs in South Tangerang City. This research used a quantitative approach with an explanatory research design. The sample consisted of food stall owners or managers who had operated for at least one year, adopted digital technology, and were directly involved in business decision-making. Data were collected through a closed-ended questionnaire using a five-point Likert scale and analyzed using Structural Equation Modeling–Partial Least Squares (SEM-PLS) with SmartPLS. The results show that Digital Capability has a positive and significant effect on Business Performance, with a path coefficient of 0.242 and a P-value of 0.042. Digital Transformation has the strongest effect, with a path coefficient of 0.356 and a P-value of 0.005. Digital Innovation also has a positive and significant effect, with a path coefficient of 0.242 and a P-value of 0.026. The R² value of 0.564 indicates that the three variables explain 56.4% of the variation in Business Performance. Therefore, this study concludes that improving MSME performance requires digital capability, business process transformation, and sustainable digital innovation.
Analysis of Cryptocurrency Investment Patterns Using Machine Learning Farrel Amri Naufal Sandio; Renny Sari Dewi
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 11 No. 2 (2026): May
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/7ny29y07

Abstract

The rapid growth of cryptocurrency, particularly Bitcoin, has introduced high-return investment opportunities accompanied by extreme price volatility, posing challenges for accurate forecasting. Previous studies have applied various machine learning models for Bitcoin price prediction; however, limited attention has been given to how different training data horizons affect model performance and generalisation. This study addresses this gap by comparing three machine learning algorithms: Linear Regression (LR), XGBoost, and Long Short-Term Memory (LSTM). The analysis examines different training periods, with a primary focus on a 3-year training scenario. Historical Bitcoin data (1-minute intervals) from Kaggle was aggregated into daily observations and processed using strict chronological splitting (80:20) without data leakage. Feature engineering was applied using lag-based variables, moving averages, and volatility indicators, whilst LSTM utilised sequence windowing with 30–60 time steps. Empirical results from the 3-year training scenario show that LR and XGBoost achieve strong predictive performance (R² = 0.9757 and 0.9667), whilst LSTM performs moderately (R² = 0.72) with higher prediction errors. Additional exploratory experiments on shorter training horizons (e.g., 6 months) indicate a decline in performance across models, reflected in unstable generalisation and negative R² values on test data, suggesting overfitting. However, directional accuracy remains above 55% in the primary scenario. These findings suggest that model performance is sensitive to the length and stability of historical data. Whilst simpler models such as linear regression and tree-based methods demonstrate consistent performance in the evaluated setting, conclusions regarding model superiority should be interpreted within the scope of the experiment.
Estimasi Biaya Website UMKM Travel Menggunakan Metode FPA, UCP, dan Hybrid Cellina Avrilia Angel; Renny Sari Dewi
Journal Automation Computer Information System Vol. 6 No. 2 (2026): November (In Progress Issue)
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/jacis.v6i2.198

Abstract

Estimasi biaya yang tidak akurat pada tahap awal pengembangan perangkat lunak dapat menyebabkan pembengkakan anggaran, terutama bagi UMKM yang memiliki keterbatasan sumber daya. Penelitian ini bertujuan membandingkan performa metode Function Point Analysis (FPA), Use Case Points (UCP), dan Hybrid FPA-UCP dalam mengestimasi biaya pengembangan website UMKM Travel. Penelitian menggunakan pendekatan kuantitatif komparatif berbasis studi kasus dengan mengonversi ukuran fungsional sistem menjadi effort dan biaya, kemudian membandingkannya dengan biaya aktual proyek. Hasil penelitian menunjukkan bahwa FPA menghasilkan estimasi biaya sebesar Rp16.195.220 dengan deviasi 9,52% (underestimate), sedangkan UCP menghasilkan estimasi Rp19.604.740 dengan deviasi 9,52% (overestimate). Model Hybrid FPA-UCP menghasilkan estimasi Rp17.900.000 dengan deviasi mendekati 0% terhadap biaya aktual. Pada studi kasus website UMKM Travel, pendekatan Hybrid FPA-UCP memberikan estimasi biaya yang paling mendekati biaya aktual dibandingkan FPA dan UCP. Temuan ini menunjukkan bahwa pendekatan hybrid berpotensi menjadi alternatif estimasi biaya untuk proyek website UMKM dengan karakteristik serupa, meskipun masih memerlukan validasi pada lebih banyak proyek
The Effect of Innovation and Digital Capital Adoption on MSME Performance Mediated by Competitive Advantage Mochammad Havid Rizqi Ramadhan; Achmad Kautsar; Renny Sari Dewi; Hujjatullah Fazlurrahman
TRANSEKONOMIKA: AKUNTANSI, BISNIS DAN KEUANGAN Vol. 5 No. 6 (2025): November 2025
Publisher : Transpublika Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55047/transekonomika.v5i6.1120

Abstract

Amid the accelerated advancement of digital technologies and the intensification of market rivalry, continuous enhancement of business performance among MSMEs has become imperative through innovation and digital transformation initiatives. Nevertheless, empirical investigations examining the contribution of digital capital adoption and innovation to MSME performance, particularly when competitive advantage functions as an intervening mechanism, remain relatively scarce, especially within regional MSME settings. This study is conducted to investigate the influence of innovation and digital capital adoption on MSME performance, with competitive advantage positioned as a mediating construct. A quantitative research design is employed, utilizing survey responses obtained from 90 MSME proprietors in Probolinggo Regency. The data that were gathered are processed and evaluated through PLS-SEM to assess both direct and indirect causal pathways among the examined variables. The results reveal that innovation is found to exert a significant positive effect on competitive advantage, which in turn is shown to significantly enhance MSME performance. On the other hand, there is no evidence that innovation directly affects the performance of MSMEs. However, adopting digital capital has been shown to have a big and positive effect on performance results. Moreover, the linkage between innovation and MSME performance is fully mediated by competitive advantage. These results suggest that innovation enhances MSME performance only when it is transformed into competitive advantage, whereas digital capital adoption directly contributes to performance improvement. Therefore, for MSME practitioners, strengthening innovation strategies oriented toward competitive differentiation and expanding the effective use of digital capital are essential to improve business performance.
Development of Audit Instruments and Maturity Assessment of Academic Information Systems Using COBIT 2019 (A Case Study at XYZ University) Putri Amaliyah; Renny Sari Dewi; Rindu Puspita Wibawa; Ainur Rofik
Journal of Digital Business and Innovation Management Vol. 4 No. 2 (2025): December 2025
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jdbim.v4i2.71242

Abstract

This study aims to evaluate the performance of the Digital Academic Information System (SISD) at XYZ University using the COBIT 2019 framework. The evaluation focuses on two core academic features—Study Plan Card (KRS) and Study Result Card (KHS)—to develop a systematic audit working paper and provide improvement recommendations. A qualitative case study approach was employed, with data collected through semi-structured interviews involving SISD administrators. The analysis was conducted descriptively based on the Deliver, Service, and Support (DSS) domain of COBIT 2019. The findings indicate that SISD has achieved Capability Level 3 (Defined), with an average score of 3.15. This study contributes a practical audit instrument and a capability improvement plan to strengthen information system governance in the higher education environment. In addition, the study offers a cost estimation to support comprehensive implementation planning.
Design of a Web Based Workshop Management Information System Application Using Rapid Application Development Techniques Nurfathan Samnaufal Razzaq; Renny Sari Dewi
Journal of Digital Business and Innovation Management Vol. 4 No. 2 (2025): December 2025
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jdbim.v4i2.71678

Abstract

The rapid pace of digital transformation across industries requires all sectors, including the automotive service industry, to adopt technology in order to enhance operational efficiency and competitiveness. This study aims to design and develop a web-based Management Information System (MIS) for CV XYZ, a workshop that has been relying on manual methods for its transaction and data recording processes. These manual practices have led to problems such as delayed recordkeeping, risk of data loss, and inaccurate inventory information. To address these issues, this research adopts a qualitative approach combined with the Rapid Application Development (RAD) method, which emphasizes speed and flexibility in system development. The process involves analyzing user needs, designing user interfaces, implementing the system, and conducting system testing. The results show that the developed web-based MIS significantly improves data management related to services, spare parts, mechanics, and transactions in a faster, more accurate, and integrated manner. User Acceptance Testing (UAT) conducted with the business owner revealed a 100% satisfaction rate with all developed system features. These findings indicate that implementing the MIS not only increases the operational efficiency of the workshop but also supports data-driven decision-making in real time. Theoretically, this research contributes to a deeper understanding of the RAD method in the context of system development for micro, small, and medium enterprises (MSMEs), and it serves as a reference for similar initiatives in other sectors.
Implementation of Enterprise Resource Planning Inventory and Point of Sales Module (Study Case at XYZ Distributor Company) Adellyna Cantica Febbyanti; Renny Sari Dewi
Journal of Digital Business and Innovation Management Vol. 4 No. 2 (2025): December 2025
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jdbim.v4i2.71684

Abstract

This study aims to implementation of an Enterprise Resource Planning (ERP) system using Inventory and Point of Sales (POS) modules in the XYZ distributor company. ERP was chosen as a solution to address the challenges faced by the company in managing stock and sales transactions, which were still performed manually, often leading to data inaccuracies and operational inefficiencies. The Quickstart Odoo method was employed for system development due to its effective, efficient, and structured approach. The research involved analyzing existing business processes, identifying gaps, and configuring the ERP system to align with the company's needs. Data collection was conducted through stakeholder interviews and literature reviews. The implementation of the Inventory module provided real-time visibility into stock levels, enhancing inventory management efficiency, while the POS module automated sales transactions and enabled real-time data consolidation.
Development of Audit Working Papers and Maturity Levels for Helpdesk Information Technology Governance Using COBIT 2019 in the DSS Domain: (A Case Study of XYZ University) Syifa'ul Aini Zahroh; Renny Sari Dewi; Rindu Puspita Wibawa
Journal of Digital Business and Innovation Management Vol. 4 No. 2 (2025): December 2025
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jdbim.v4i2.71778

Abstract

The implementation of the helpdesk information system at University XZY in Surabaya plays a crucial role in supporting the management of complaints from students and academic staff. However, several issues have been identified, including inadequate user data verification mechanisms, potential privacy violations due to open access to complaint reports by other users, and the absence of a structured incident resolution report. These challenges impact the performance and integrity of the information system. To address these problems, this study aims to design an audit working paper using the COBIT 2019 framework, specifically focusing on DSS02 (Managed Service Requests and Incidents), DSS03 (Managed Problems), and DSS04 (Managed Continuity) to evaluate and improve the system. The findings indicate that all three domains are at capability level 3 (Defined), which implies that processes are documented but not yet measured consistently. This study produces an audit working paper, improvement recommendations, and an implementation cost estimation, which can serve as a strategic reference for university XYZ in enhancing the quality, security, and sustainability of its helpdesk system.
Co-Authors A. Holil Noor Ali Abdul Mun’im Taufik Nugraha Achmad Dzikrul Baqi Achmad Fitro Achmad Kautsar Achmad Kautsar Adellyna Cantica Febbyanti Agung Kurniawan Ainur Rofik Alvian Yoga Saputra Amaliyah, Putri Amelia Hayyu Astiarasanti Anindra, Nisya Kayla Putri Archam Zahidin Arifah, Ika Diyah Candra Astiarasanti, Amelia Hayyu Astrid Dyssa Rachmawati Atika Naiylatan Syirfa Baqi, Achmad Dzikrul Candra Bagus Ainur Rochman Candra, Ika Diyah Cellina Avrilia Angel Damayanti, Yeni Rosa Darmawan, Rafli Dewangga Lazuardi Ramadhan Dhito Aji Tri Prabowo Dhiyan Septa Wihara Dhya Aminaturrahmah Dicka Widya Purnama Dini Idzni Izatri Dwipa, Elfara Fraksi Dzhuri Lintang P Dzhuri Lintang P Elok Tiara Cahya Septi Ermawati, Juliana Fahmi, Fiqih Zulfikar Farrel Amri Naufal Sandio Fathimah Az Zahrah Fatimah Chibbatullah Fazlurrahman, Hujjatullah Firdayatul Dewi Sartika Fresha Kharisma Gyansar Pralebda Hadi, Hafid Kholidi Hanim Maria Astuti Huanggino, Sherissa Callista Hujjatullah Fazlurrahman Hujjatullah Fazlurrahman I Ketut Ari Sadhu Gunawan Ilham Cahya Putra Ramadan Jayadi, Puguh Jaziz Waha Bidha Sani Jaziz Waha Bidha Sani Juliana Kristi Juliana Kristi Juliana Kristi Kautsar, Achmad Kawakib, Afif Nurul Lestiani, Dwi Indah Lovita Lisa Nur Afifah M. Adhi Putra Benowo Marsekal Dadrian Setyayudha Maulidan Bagus A. Rasyid Maulidina, Rahma Maulidiyah, Sri Moch Aldoris Williandy Mochammad Havid Rizqi Ramadhan Mohammad Adam Prasetyo Mohammad Imamuddin Adani Muhammad Bayu Nugraha Muhammad Chabibi Muhammad Choirul Rozikin Muhammad Fachmi Muhammad Fajar Wahyudi Rahman Muhammad Febrilian Dwi Syahputra Febri Muhammad Ibrahim Adham Karim Muthoharoh, Imroatul Nadia Asandimitra Haryono Nisa Uzahrok Nofita Idaroka Rohmah Nugraini, Dian Nur Alfiyah Miftakhul Jannah Nur Kholifathin Nadhiroh Nurfathan Samnaufal Razzaq Priambodo, Gumilang Puguh Jayadi Purnama, Dicka Widya Puspitasari, Reinindhi Putri Amaliyah Putri Amaliyah Putri, Ella Rosediana Rafli Darmawan Ramadhan, Mochammad Havid Rizqi Ramadhany Candra A.P. Ratih Amelia Rayhan Aimar Nawawi Reihan, Givvara Rijal, Demas Muhammad Rindu Puspita Wibawa Rindu Puspita Wibawa Rindu Puspita Wibawa Riska Dhenabayu Riska Dhenabayu Rizki, Nur Anisa Rochman, Candra Bagus Ainur Ronie Febriansyah Rosmalia, Tria Rizky Sandhea, Annisa Azzar Sari Setyaningsih Sayekti, Widya Setya Suprayogi Siti Nur Aisah Sri Anardani Sugiono, Adinda Ayu Putri Sussolaikah, Kelik Syawalludin, Syawalludin Syifa'ul Aini Zahroh Syirfa, Atika Naylatan Trias Widha Andari Wijaya, Anne Ivena Yarbo, Aqeela Istighfarin Zahidin, Archam Zamabhungane Hadebe Aminah