Claim Missing Document
Check
Articles

Found 3 Documents
Search

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 (Article in Progress)
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.
From Voice to Ease of Purchase: Analysis of Voice Search and Perceived Ease of Use on Purchase Intention Rizki Rahmawati; A. Al-Kairana Mazaya; Hafidzah Aryani; Tria Rizky Rosmalia; Muhammad Fajar Wahyudi Rahman; Thanh Ngan Bui
Journal of Digital Business and Innovation Management Vol. 5 No. 1 (2026): June 2026
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jdbim.v5i1.73982

Abstract

Perkembangan teknologi digital dan peningkatan penggunaan smartphone telah mengubah perilaku belanja online di Indonesia, terutama melalui proses pencarian dan transaksi yang lebih cepat dan mudah. Dalam konteks ini, pencarian suara dan kemudahan penggunaan yang dirasakan telah menjadi faktor penting dalam membentuk niat pembelian konsumen. Studi ini bertujuan untuk menganalisis pengaruh pencarian suara dan kemudahan penggunaan yang dirasakan terhadap niat pembelian di kalangan pengguna aplikasi Lazada. Penelitian ini menggunakan pendekatan kuantitatif dengan melibatkan 150 responden yang telah menggunakan fitur pencarian suara dalam tiga bulan terakhir. Data dikumpulkan melalui kuesioner online dengan skala Likert 5 poin dan dianalisis menggunakan SmartPLS. Analisis menunjukkan bahwa pencarian suara memiliki pengaruh positif dan signifikan terhadap niat pembelian, dengan nilai t-statistic sebesar 4.031, yang menunjukkan bahwa semakin baik kualitas dan kemudahan fitur pencarian suara, semakin tinggi niat konsumen untuk membeli. Selain itu, kemudahan penggunaan yang dirasakan juga memiliki pengaruh positif dan signifikan, dengan nilai t-statistic sebesar 6.784, dan pengaruhnya lebih kuat daripada pencarian suara. Temuan ini konsisten dengan Model Penerimaan Teknologi (TAM), yang menekankan bahwa Kemudahan Penggunaan yang Dirasakan dari suatu teknologi dapat meningkatkan niat pembelian konsumen.
The Role Of Digital Payment Mediation In The Adoption Of Digital Technology To Improve The Performance Of MSMEs In Tuban Regency Nara Dea Atha Raya; Achmad Kautsar; Nanang Hoesen Hidroes Abbrori; Muhammad Fajar Wahyudi Rahman
International Journal Of Humanities Education and Social Sciences (IJHESS) Vol 5 No 5 (2026): IJHESS APRIL 2026
Publisher : CV. AFDIFAL MAJU BERKAH

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55227/ijhess.v5i5.2298

Abstract

Objective – This study aims to analyze the effect of technology adoption on the performance of Micro, Small, and Medium Enterprises (MSMEs) in Tuban Regency and to examine the role of digital payment as a mediating variable in this relationship. The adoption of digital technologies and payment systems is expected to improve transaction efficiency, accelerate cash flow, and enhance financial transparency, which may ultimately improve MSME performance. Design/Methodology/Approach – This study uses a quantitative research design with a survey approach involving MSME actors in Tuban Regency. Data were collected through questionnaires distributed to MSME owners and managers. The analysis was conducted using Partial Least Squares–Structural Equation Modeling (PLS-SEM) to test the direct and indirect relationships between technology adoption, digital payment usage, and MSME performance. Findings – The results show that technology adoption has a positive and significant effect on MSME performance. In addition, technology adoption significantly influences the use of digital payment systems. Digital payment also has a positive and significant effect on MSME performance and acts as a mediating variable that strengthens the relationship between technology adoption and MSME performance. Implications – The originality of this study lies in examining the mediating role of digital payment in the relationship between technology adoption and MSME performance within the context of local MSMEs in Tuban Regency. The findings provide theoretical contributions to digital technology adoption research and practical implications for policymakers and MSME stakeholders in encouraging digital transformation to improve competitiveness and sustainability in the digital economy.